avihaig's picture
Add the 39 final checkpoints and their run records (part 2)
f4c01f9 verified
Raw History Blame Contribute Delete
17 kB
{"step": 500, "train_loss": 0.1210133507847786, "eval_loss": 0.06344475108198822}
{"step": 1000, "train_loss": 0.08578335493803024, "eval_loss": 0.06259498529834673}
{"step": 1500, "train_loss": 0.06919616460800171, "eval_loss": 0.058933610387612134}
{"step": 2000, "train_loss": 0.16819848120212555, "eval_loss": 0.06239608535543084}
{"step": 2500, "train_loss": 0.1869126707315445, "eval_loss": 0.05788549513090402}
{"step": 3000, "train_loss": 0.08450300991535187, "eval_loss": 0.06119792000390589}
{"step": 3500, "train_loss": 0.0711706206202507, "eval_loss": 0.05961441085673869}
{"step": 4000, "train_loss": 0.18338122963905334, "eval_loss": 0.051783554372377694}
{"step": 4500, "train_loss": 0.1913202852010727, "eval_loss": 0.05406384484376758}
{"step": 5000, "train_loss": 0.05668133124709129, "eval_loss": 0.049126818892546}
{"step": 5500, "train_loss": 0.2558148205280304, "eval_loss": 0.05625929677626118}
{"step": 6000, "train_loss": 0.1187107041478157, "eval_loss": 0.04905811359640211}
{"step": 6500, "train_loss": 0.106544628739357, "eval_loss": 0.05044242733856663}
{"step": 7000, "train_loss": 0.0873526856303215, "eval_loss": 0.05385531991487369}
{"step": 7500, "train_loss": 0.12496069818735123, "eval_loss": 0.04676190990721807}
{"step": 8000, "train_loss": 0.204632967710495, "eval_loss": 0.050440958875697106}
{"step": 8500, "train_loss": 0.10313089936971664, "eval_loss": 0.04883839614922181}
{"step": 9000, "train_loss": 0.0620700903236866, "eval_loss": 0.0469757046084851}
{"step": 9500, "train_loss": 0.053480301052331924, "eval_loss": 0.04609489539870992}
{"step": 10000, "train_loss": 0.21171434223651886, "eval_loss": 0.05045570194488391}
{"step": 10500, "train_loss": 0.16739903390407562, "eval_loss": 0.054563640092965215}
{"step": 11000, "train_loss": 0.20471835136413574, "eval_loss": 0.043888077314477414}
{"step": 11500, "train_loss": 0.09749025106430054, "eval_loss": 0.047989977698307484}
{"step": 12000, "train_loss": 0.043582983314991, "eval_loss": 0.04871807707240805}
{"step": 12500, "train_loss": 0.18310488760471344, "eval_loss": 0.0478669666335918}
{"step": 13000, "train_loss": 0.16296809911727905, "eval_loss": 0.04264456784585491}
{"step": 13500, "train_loss": 0.1133088618516922, "eval_loss": 0.0524186622351408}
{"step": 14000, "train_loss": 0.18397030234336853, "eval_loss": 0.04875742213334888}
{"step": 14500, "train_loss": 0.14561215043067932, "eval_loss": 0.05061605415539816}
{"step": 15000, "train_loss": 0.10117877274751663, "eval_loss": 0.04837332514580339}
{"step": 15500, "train_loss": 0.09550070762634277, "eval_loss": 0.04772578430129215}
{"step": 16000, "train_loss": 0.19604873657226562, "eval_loss": 0.047056227282155305}
{"step": 16500, "train_loss": 0.15880225598812103, "eval_loss": 0.0470902492525056}
{"step": 17000, "train_loss": 0.0521564856171608, "eval_loss": 0.042735997354611754}
{"step": 17500, "train_loss": 0.07339780777692795, "eval_loss": 0.04129070014460012}
{"step": 18000, "train_loss": 0.09072379022836685, "eval_loss": 0.045537438767496496}
{"step": 18500, "train_loss": 0.05881557613611221, "eval_loss": 0.0448674131766893}
{"step": 19000, "train_loss": 0.0469968244433403, "eval_loss": 0.04066693695494905}
{"step": 19500, "train_loss": 0.05653830245137215, "eval_loss": 0.04631103144492954}
{"step": 20000, "train_loss": 0.10621097683906555, "eval_loss": 0.04691630933666602}
{"step": 20500, "train_loss": 0.09373657405376434, "eval_loss": 0.04224610864184797}
{"step": 21000, "train_loss": 0.22968678176403046, "eval_loss": 0.04684432956855744}
{"step": 21500, "train_loss": 0.05570029094815254, "eval_loss": 0.04460225813090801}
{"step": 22000, "train_loss": 0.17573700845241547, "eval_loss": 0.04598592803813517}
{"step": 22500, "train_loss": 0.05122148245573044, "eval_loss": 0.04752684634877369}
{"step": 23000, "train_loss": 0.05129750072956085, "eval_loss": 0.04532553389435634}
{"step": 23500, "train_loss": 0.05714135244488716, "eval_loss": 0.0479350020759739}
{"step": 24000, "train_loss": 0.11438502371311188, "eval_loss": 0.045150533493142575}
{"step": 24500, "train_loss": 0.2021285891532898, "eval_loss": 0.0452744061476551}
{"step": 25000, "train_loss": 0.06869187206029892, "eval_loss": 0.04733782424591482}
{"step": 25500, "train_loss": 0.049366552382707596, "eval_loss": 0.04074914270313457}
{"step": 26000, "train_loss": 0.059900082647800446, "eval_loss": 0.042421001417096704}
{"step": 26500, "train_loss": 0.05384938418865204, "eval_loss": 0.047798865009099245}
{"step": 27000, "train_loss": 0.05081050470471382, "eval_loss": 0.04604562860913575}
{"step": 27500, "train_loss": 0.0924643725156784, "eval_loss": 0.043419015244580805}
{"step": 28000, "train_loss": 0.05392333120107651, "eval_loss": 0.044387198868207633}
{"step": 28500, "train_loss": 0.19457568228244781, "eval_loss": 0.043086446064990014}
{"step": 29000, "train_loss": 0.05202091112732887, "eval_loss": 0.044358845450915396}
{"step": 29500, "train_loss": 0.05745166540145874, "eval_loss": 0.043307061307132244}
{"step": 30000, "train_loss": 0.04863230511546135, "eval_loss": 0.04891916405176744}
{"step": 30500, "train_loss": 0.19495192170143127, "eval_loss": 0.04577136953594163}
{"step": 31000, "train_loss": 0.04469282925128937, "eval_loss": 0.04292322898982093}
{"step": 31500, "train_loss": 0.047907132655382156, "eval_loss": 0.042745098704472184}
{"step": 32000, "train_loss": 0.18052835762500763, "eval_loss": 0.038509332633111626}
{"step": 32500, "train_loss": 0.20078246295452118, "eval_loss": 0.04370544687844813}
{"step": 33000, "train_loss": 0.06531178206205368, "eval_loss": 0.04149643884738907}
{"step": 33500, "train_loss": 0.1792861670255661, "eval_loss": 0.042281142028514296}
{"step": 34000, "train_loss": 0.08181439340114594, "eval_loss": 0.04441239463631064}
{"step": 34500, "train_loss": 0.055291373282670975, "eval_loss": 0.042767650564201176}
{"step": 35000, "train_loss": 0.05058017745614052, "eval_loss": 0.0438882383168675}
{"step": 35500, "train_loss": 0.05126228183507919, "eval_loss": 0.043825108208693564}
{"step": 36000, "train_loss": 0.13664469122886658, "eval_loss": 0.04566131118917838}
{"step": 36500, "train_loss": 0.149209663271904, "eval_loss": 0.04256148432614282}
{"step": 37000, "train_loss": 0.04923190549015999, "eval_loss": 0.04098172881640494}
{"step": 37500, "train_loss": 0.2389589101076126, "eval_loss": 0.0447357582161203}
{"step": 38000, "train_loss": 0.17976221442222595, "eval_loss": 0.04078388790367171}
{"step": 38500, "train_loss": 0.1991366595029831, "eval_loss": 0.04057294240919873}
{"step": 39000, "train_loss": 0.21631556749343872, "eval_loss": 0.04020274244248867}
{"step": 39500, "train_loss": 0.052984170615673065, "eval_loss": 0.04396423127036542}
{"step": 40000, "train_loss": 0.03953852877020836, "eval_loss": 0.03946913278196007}
{"step": 40500, "train_loss": 0.15060728788375854, "eval_loss": 0.041743477690033615}
{"step": 41000, "train_loss": 0.08624401688575745, "eval_loss": 0.04346638126298785}
{"step": 41500, "train_loss": 0.2577853202819824, "eval_loss": 0.044298977532889694}
{"step": 42000, "train_loss": 0.041217029094696045, "eval_loss": 0.043639131472446024}
{"step": 42500, "train_loss": 0.07124992460012436, "eval_loss": 0.04062443581642583}
{"step": 43000, "train_loss": 0.04820876568555832, "eval_loss": 0.040431211644317955}
{"step": 43500, "train_loss": 0.04581465944647789, "eval_loss": 0.043345443380530924}
{"step": 44000, "train_loss": 0.14324074983596802, "eval_loss": 0.042163391306530684}
{"step": 44500, "train_loss": 0.14387093484401703, "eval_loss": 0.04386121249990538}
{"step": 45000, "train_loss": 0.056491561233997345, "eval_loss": 0.04221158445579931}
{"step": 45500, "train_loss": 0.04623355716466904, "eval_loss": 0.0430257860571146}
{"step": 46000, "train_loss": 0.14969471096992493, "eval_loss": 0.04052350332494825}
{"step": 46500, "train_loss": 0.19031359255313873, "eval_loss": 0.04082243039738387}
{"step": 47000, "train_loss": 0.04913923516869545, "eval_loss": 0.040572201542090625}
{"step": 47500, "train_loss": 0.05223236605525017, "eval_loss": 0.042402386548928916}
{"step": 48000, "train_loss": 0.12638899683952332, "eval_loss": 0.04353968315990642}
{"step": 48500, "train_loss": 0.0958222895860672, "eval_loss": 0.042316739505622536}
{"step": 49000, "train_loss": 0.07610712945461273, "eval_loss": 0.043341816344764084}
{"step": 49500, "train_loss": 0.04848498851060867, "eval_loss": 0.03983255795901641}
{"step": 50000, "train_loss": 0.10599623620510101, "eval_loss": 0.040327481750864536}
{"step": 50500, "train_loss": 0.07462653517723083, "eval_loss": 0.04332778399111703}
{"step": 51000, "train_loss": 0.04797337204217911, "eval_loss": 0.04164407344069332}
{"step": 51500, "train_loss": 0.12890757620334625, "eval_loss": 0.043739173852372915}
{"step": 52000, "train_loss": 0.18072453141212463, "eval_loss": 0.042911644151899964}
{"step": 52500, "train_loss": 0.0530373640358448, "eval_loss": 0.042396731092594564}
{"step": 53000, "train_loss": 0.044049426913261414, "eval_loss": 0.04376480350038037}
{"step": 53500, "train_loss": 0.10266992449760437, "eval_loss": 0.04083583899773657}
{"step": 54000, "train_loss": 0.04180388152599335, "eval_loss": 0.04033107927534729}
{"step": 54500, "train_loss": 0.0383603610098362, "eval_loss": 0.04249754367629066}
{"step": 55000, "train_loss": 0.08712835609912872, "eval_loss": 0.040798333240672946}
{"step": 55500, "train_loss": 0.043114073574543, "eval_loss": 0.04130338010145351}
{"step": 56000, "train_loss": 0.19868585467338562, "eval_loss": 0.0424009328125976}
{"step": 56500, "train_loss": 0.12068941444158554, "eval_loss": 0.04272235231474042}
{"step": 57000, "train_loss": 0.053707439452409744, "eval_loss": 0.041792777308728546}
{"step": 57500, "train_loss": 0.037642013281583786, "eval_loss": 0.03968217957299203}
{"step": 58000, "train_loss": 0.0393468402326107, "eval_loss": 0.04014491458656266}
{"step": 58500, "train_loss": 0.04664768651127815, "eval_loss": 0.04076771537074819}
{"step": 59000, "train_loss": 0.05124818533658981, "eval_loss": 0.040256611828226596}
{"step": 59500, "train_loss": 0.17389538884162903, "eval_loss": 0.04201831348473206}
{"step": 60000, "train_loss": 0.04923117905855179, "eval_loss": 0.04271200019866228}
{"step": 60500, "train_loss": 0.21097037196159363, "eval_loss": 0.04119834321318194}
{"step": 61000, "train_loss": 0.042796626687049866, "eval_loss": 0.040299380489159375}
{"step": 61500, "train_loss": 0.08158367872238159, "eval_loss": 0.03969287971267477}
{"step": 62000, "train_loss": 0.044333525002002716, "eval_loss": 0.039216265198774636}
{"step": 62500, "train_loss": 0.1268274188041687, "eval_loss": 0.04104212817037478}
{"step": 63000, "train_loss": 0.07856572419404984, "eval_loss": 0.03897050052182749}
{"step": 63500, "train_loss": 0.13350920379161835, "eval_loss": 0.04424295364879072}
{"step": 64000, "train_loss": 0.08862541615962982, "eval_loss": 0.04173692857148126}
{"step": 64500, "train_loss": 0.04126337915658951, "eval_loss": 0.04071054182713851}
{"step": 65000, "train_loss": 0.17132429778575897, "eval_loss": 0.04119197832187638}
{"step": 65500, "train_loss": 0.10294121503829956, "eval_loss": 0.04118260246468708}
{"step": 66000, "train_loss": 0.12088745832443237, "eval_loss": 0.04221090878127143}
{"step": 66500, "train_loss": 0.050038572400808334, "eval_loss": 0.04387433221563697}
{"step": 67000, "train_loss": 0.09087629616260529, "eval_loss": 0.04030278360005468}
{"step": 67500, "train_loss": 0.1521265208721161, "eval_loss": 0.04113210929790512}
{"step": 68000, "train_loss": 0.04507727921009064, "eval_loss": 0.04128082509851083}
{"step": 68500, "train_loss": 0.0770777091383934, "eval_loss": 0.04207228583982214}
{"step": 69000, "train_loss": 0.13917779922485352, "eval_loss": 0.043206030095461756}
{"step": 69500, "train_loss": 0.044784314930438995, "eval_loss": 0.041892939421813935}
{"step": 70000, "train_loss": 0.04905609041452408, "eval_loss": 0.04257368191611022}
{"step": 70500, "train_loss": 0.043513692915439606, "eval_loss": 0.042555904074106365}
{"step": 71000, "train_loss": 0.17866431176662445, "eval_loss": 0.04265165701508522}
{"step": 71500, "train_loss": 0.06243963912129402, "eval_loss": 0.04215780080994591}
{"step": 72000, "train_loss": 0.04307658225297928, "eval_loss": 0.04124585405224934}
{"step": 72500, "train_loss": 0.1377684473991394, "eval_loss": 0.04187366337282583}
{"step": 73000, "train_loss": 0.07278904318809509, "eval_loss": 0.04117223824141547}
{"step": 73500, "train_loss": 0.04125944897532463, "eval_loss": 0.0419336807099171}
{"step": 74000, "train_loss": 0.04278901591897011, "eval_loss": 0.04120027588214725}
{"step": 74500, "train_loss": 0.0372769869863987, "eval_loss": 0.04023237660294399}
{"step": 75000, "train_loss": 0.03300147131085396, "eval_loss": 0.04129641177132726}
{"step": 75500, "train_loss": 0.05302021652460098, "eval_loss": 0.04168261954328045}
{"step": 76000, "train_loss": 0.18247422575950623, "eval_loss": 0.041598946729209274}
{"step": 76500, "train_loss": 0.09701869636774063, "eval_loss": 0.04024306091014296}
{"step": 77000, "train_loss": 0.17466957867145538, "eval_loss": 0.04168372170533985}
{"step": 77500, "train_loss": 0.08479811251163483, "eval_loss": 0.040610642347019166}
{"step": 78000, "train_loss": 0.07233636826276779, "eval_loss": 0.039959279471077025}
{"step": 78500, "train_loss": 0.03216071426868439, "eval_loss": 0.04022777150385082}
{"step": 79000, "train_loss": 0.051210321485996246, "eval_loss": 0.04013436275999993}
{"step": 79500, "train_loss": 0.11824506521224976, "eval_loss": 0.04060478473547846}
{"step": 80000, "train_loss": 0.13417711853981018, "eval_loss": 0.042059776722453535}
{"step": 80500, "train_loss": 0.1267964094877243, "eval_loss": 0.03924983076285571}
{"step": 81000, "train_loss": 0.15649741888046265, "eval_loss": 0.040161979326512665}
{"step": 81500, "train_loss": 0.0704650953412056, "eval_loss": 0.042308178381063044}
{"step": 82000, "train_loss": 0.1407831907272339, "eval_loss": 0.040456233196891844}
{"step": 82500, "train_loss": 0.18847303092479706, "eval_loss": 0.04172175488201901}
{"step": 83000, "train_loss": 0.052719876170158386, "eval_loss": 0.040650214185006917}
{"step": 83500, "train_loss": 0.03692108392715454, "eval_loss": 0.04079427383840084}
{"step": 84000, "train_loss": 0.1716684252023697, "eval_loss": 0.04128655360545963}
{"step": 84500, "train_loss": 0.15489833056926727, "eval_loss": 0.03972168831387535}
{"step": 85000, "train_loss": 0.09527426213026047, "eval_loss": 0.03916840226156637}
{"step": 85500, "train_loss": 0.17860329151153564, "eval_loss": 0.04135352693265304}
{"step": 86000, "train_loss": 0.07178670912981033, "eval_loss": 0.03993306972552091}
{"step": 86500, "train_loss": 0.11864641308784485, "eval_loss": 0.04214561654953286}
{"step": 87000, "train_loss": 0.130703404545784, "eval_loss": 0.04194941825699061}
{"step": 87500, "train_loss": 0.06800003349781036, "eval_loss": 0.03961652610450983}
{"step": 88000, "train_loss": 0.1330323964357376, "eval_loss": 0.040989820030517876}
{"step": 88500, "train_loss": 0.05153154954314232, "eval_loss": 0.0405978235648945}
{"step": 89000, "train_loss": 0.045008379966020584, "eval_loss": 0.0413986875792034}
{"step": 89500, "train_loss": 0.10604070127010345, "eval_loss": 0.04076973255723715}
{"step": 90000, "train_loss": 0.1360316425561905, "eval_loss": 0.04118872043909505}
{"step": 90500, "train_loss": 0.05067726597189903, "eval_loss": 0.0409029241418466}
{"step": 91000, "train_loss": 0.1769748479127884, "eval_loss": 0.040408031665720046}
{"step": 91500, "train_loss": 0.03808308765292168, "eval_loss": 0.0427971031749621}
{"step": 92000, "train_loss": 0.04854172468185425, "eval_loss": 0.039668765966780484}
{"step": 92500, "train_loss": 0.03810650110244751, "eval_loss": 0.04172492929501459}
{"step": 93000, "train_loss": 0.04595910757780075, "eval_loss": 0.04156127740861848}
{"step": 93500, "train_loss": 0.03820202872157097, "eval_loss": 0.04143151518655941}
{"step": 94000, "train_loss": 0.04212351515889168, "eval_loss": 0.04081241472158581}
{"step": 94500, "train_loss": 0.05147921293973923, "eval_loss": 0.04152337770210579}
{"step": 95000, "train_loss": 0.0301445834338665, "eval_loss": 0.040307311865035444}
{"step": 95500, "train_loss": 0.0741473138332367, "eval_loss": 0.04073657817207277}
{"step": 96000, "train_loss": 0.11782873421907425, "eval_loss": 0.04048929538112134}
{"step": 96500, "train_loss": 0.12145876884460449, "eval_loss": 0.040775221074}
{"step": 97000, "train_loss": 0.1839548945426941, "eval_loss": 0.03903526795329526}
{"step": 97500, "train_loss": 0.13659247756004333, "eval_loss": 0.04208568431204185}
{"step": 98000, "train_loss": 0.1332789659500122, "eval_loss": 0.04126207437366247}
{"step": 98500, "train_loss": 0.12793555855751038, "eval_loss": 0.041179096151608974}
{"step": 99000, "train_loss": 0.03323306143283844, "eval_loss": 0.03974374139215797}
{"step": 99500, "train_loss": 0.09042960405349731, "eval_loss": 0.040377886791247874}
{"step": 100000, "train_loss": 0.04054075479507446, "eval_loss": 0.03986038756556809}