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": 0.1041671484708786, "eval_loss": 0.08439801749773324}
{"step": 1000, "train_loss": 0.2234959900379181, "eval_loss": 0.048561157076619565}
{"step": 1500, "train_loss": 0.2612881660461426, "eval_loss": 0.07105436729034409}
{"step": 2000, "train_loss": 0.06145403906702995, "eval_loss": 0.057850542361848056}
{"step": 2500, "train_loss": 0.17447997629642487, "eval_loss": 0.06305587518727407}
{"step": 3000, "train_loss": 0.2357759177684784, "eval_loss": 0.051185078104026616}
{"step": 3500, "train_loss": 0.39497923851013184, "eval_loss": 0.05777482222765684}
{"step": 4000, "train_loss": 0.10895899683237076, "eval_loss": 0.05144932016264647}
{"step": 4500, "train_loss": 0.09698067605495453, "eval_loss": 0.05253045214340091}
{"step": 5000, "train_loss": 0.06742649525403976, "eval_loss": 0.05505773704499006}
{"step": 5500, "train_loss": 0.0642765536904335, "eval_loss": 0.05785249575274065}
{"step": 6000, "train_loss": 0.10807482153177261, "eval_loss": 0.055937353463377804}
{"step": 6500, "train_loss": 0.057081710547208786, "eval_loss": 0.049449163081590086}
{"step": 7000, "train_loss": 0.10065240412950516, "eval_loss": 0.04841309896437451}
{"step": 7500, "train_loss": 0.10069012641906738, "eval_loss": 0.05446635471889749}
{"step": 8000, "train_loss": 0.17203915119171143, "eval_loss": 0.05135954433353618}
{"step": 8500, "train_loss": 0.06105648726224899, "eval_loss": 0.04968974378425628}
{"step": 9000, "train_loss": 0.056201010942459106, "eval_loss": 0.046448759094346315}
{"step": 9500, "train_loss": 0.05446634441614151, "eval_loss": 0.04068265832029283}
{"step": 10000, "train_loss": 0.12556558847427368, "eval_loss": 0.04022232355782762}
{"step": 10500, "train_loss": 0.2740843892097473, "eval_loss": 0.053415476402733475}
{"step": 11000, "train_loss": 0.055774908512830734, "eval_loss": 0.04550852224929258}
{"step": 11500, "train_loss": 0.1051502674818039, "eval_loss": 0.04473941586911678}
{"step": 12000, "train_loss": 0.20425696671009064, "eval_loss": 0.043709461810067296}
{"step": 12500, "train_loss": 0.07214783877134323, "eval_loss": 0.049147491925396025}
{"step": 13000, "train_loss": 0.10923724621534348, "eval_loss": 0.043246063869446516}
{"step": 13500, "train_loss": 0.04584570229053497, "eval_loss": 0.03912475472316146}
{"step": 14000, "train_loss": 0.1640198975801468, "eval_loss": 0.045357256196439266}
{"step": 14500, "train_loss": 0.04614940658211708, "eval_loss": 0.04477459052577615}
{"step": 15000, "train_loss": 0.05829988420009613, "eval_loss": 0.041731113626156}
{"step": 15500, "train_loss": 0.14936360716819763, "eval_loss": 0.0456416952656582}
{"step": 16000, "train_loss": 0.09638448059558868, "eval_loss": 0.038918326783459634}
{"step": 16500, "train_loss": 0.05278573930263519, "eval_loss": 0.04160845302976668}
{"step": 17000, "train_loss": 0.15211589634418488, "eval_loss": 0.039435247832443565}
{"step": 17500, "train_loss": 0.05502414330840111, "eval_loss": 0.04016348230652511}
{"step": 18000, "train_loss": 0.06504388898611069, "eval_loss": 0.03981186397140846}
{"step": 18500, "train_loss": 0.056413523852825165, "eval_loss": 0.04339525458635762}
{"step": 19000, "train_loss": 0.05347355082631111, "eval_loss": 0.04185353918001056}
{"step": 19500, "train_loss": 0.20382316410541534, "eval_loss": 0.04090156493475661}
{"step": 20000, "train_loss": 0.09741846472024918, "eval_loss": 0.03921283024828881}
{"step": 20500, "train_loss": 0.11542501300573349, "eval_loss": 0.04315530665917322}
{"step": 21000, "train_loss": 0.1364186853170395, "eval_loss": 0.038031434174627066}
{"step": 21500, "train_loss": 0.0523877777159214, "eval_loss": 0.04674530535703525}
{"step": 22000, "train_loss": 0.09854340553283691, "eval_loss": 0.04460387158906087}
{"step": 22500, "train_loss": 0.055441953241825104, "eval_loss": 0.04116235737456009}
{"step": 23000, "train_loss": 0.14451152086257935, "eval_loss": 0.04200949484948069}
{"step": 23500, "train_loss": 0.08364316821098328, "eval_loss": 0.04026252741459757}
{"step": 24000, "train_loss": 0.15454411506652832, "eval_loss": 0.03822940378449857}
{"step": 24500, "train_loss": 0.08170433342456818, "eval_loss": 0.043863604485522956}
{"step": 25000, "train_loss": 0.18005312979221344, "eval_loss": 0.040179374045692384}
{"step": 25500, "train_loss": 0.09268432855606079, "eval_loss": 0.040717729076277465}
{"step": 26000, "train_loss": 0.09535948187112808, "eval_loss": 0.04061125696171075}
{"step": 26500, "train_loss": 0.06705912947654724, "eval_loss": 0.04595054511446506}
{"step": 27000, "train_loss": 0.18553557991981506, "eval_loss": 0.04300893563777208}
{"step": 27500, "train_loss": 0.08179539442062378, "eval_loss": 0.040184130251873285}
{"step": 28000, "train_loss": 0.046968162059783936, "eval_loss": 0.039433180005289614}
{"step": 28500, "train_loss": 0.2082703858613968, "eval_loss": 0.040415639930870384}
{"step": 29000, "train_loss": 0.07532551139593124, "eval_loss": 0.04069286084268242}
{"step": 29500, "train_loss": 0.08249171823263168, "eval_loss": 0.03846305684419349}
{"step": 30000, "train_loss": 0.04496967792510986, "eval_loss": 0.03907110163709149}
{"step": 30500, "train_loss": 0.09266959130764008, "eval_loss": 0.04203804163262248}
{"step": 31000, "train_loss": 0.21538273990154266, "eval_loss": 0.04150275676511228}
{"step": 31500, "train_loss": 0.09413541853427887, "eval_loss": 0.04140527546405792}
{"step": 32000, "train_loss": 0.06010899320244789, "eval_loss": 0.04051003360655159}
{"step": 32500, "train_loss": 0.08286239206790924, "eval_loss": 0.04065309150610119}
{"step": 33000, "train_loss": 0.10370228439569473, "eval_loss": 0.04008222097763792}
{"step": 33500, "train_loss": 0.054841529577970505, "eval_loss": 0.038167612394317985}
{"step": 34000, "train_loss": 0.1862202286720276, "eval_loss": 0.04553809983190149}
{"step": 34500, "train_loss": 0.14266318082809448, "eval_loss": 0.04214961000252515}
{"step": 35000, "train_loss": 0.05100911855697632, "eval_loss": 0.03987202845746651}
{"step": 35500, "train_loss": 0.06816886365413666, "eval_loss": 0.04232071427395567}
{"step": 36000, "train_loss": 0.10179047286510468, "eval_loss": 0.04049323539948091}
{"step": 36500, "train_loss": 0.09204979240894318, "eval_loss": 0.04052323795622215}
{"step": 37000, "train_loss": 0.11488384753465652, "eval_loss": 0.04189019580371678}
{"step": 37500, "train_loss": 0.1295519769191742, "eval_loss": 0.039210181101225317}
{"step": 38000, "train_loss": 0.19955532252788544, "eval_loss": 0.0389372844947502}
{"step": 38500, "train_loss": 0.048624370247125626, "eval_loss": 0.038386946136597544}
{"step": 39000, "train_loss": 0.18255597352981567, "eval_loss": 0.04560061974916607}
{"step": 39500, "train_loss": 0.19511394202709198, "eval_loss": 0.038899736129678786}
{"step": 40000, "train_loss": 0.1797979772090912, "eval_loss": 0.0409198283450678}
{"step": 40500, "train_loss": 0.05556870996952057, "eval_loss": 0.03852590324822813}
{"step": 41000, "train_loss": 0.09667862951755524, "eval_loss": 0.0410935347317718}
{"step": 41500, "train_loss": 0.16169142723083496, "eval_loss": 0.038286242343019694}
{"step": 42000, "train_loss": 0.04957416281104088, "eval_loss": 0.04097026196541265}
{"step": 42500, "train_loss": 0.16718685626983643, "eval_loss": 0.040402896876912564}
{"step": 43000, "train_loss": 0.05516527220606804, "eval_loss": 0.03900306829018518}
{"step": 43500, "train_loss": 0.18122220039367676, "eval_loss": 0.03854975907597691}
{"step": 44000, "train_loss": 0.04089638590812683, "eval_loss": 0.04190220916643739}
{"step": 44500, "train_loss": 0.16026365756988525, "eval_loss": 0.041247184155508876}
{"step": 45000, "train_loss": 0.0492410771548748, "eval_loss": 0.03805987152736634}
{"step": 45500, "train_loss": 0.055521998554468155, "eval_loss": 0.0389397885883227}
{"step": 46000, "train_loss": 0.09861348569393158, "eval_loss": 0.03914271859684959}
{"step": 46500, "train_loss": 0.1763443946838379, "eval_loss": 0.03962669539032504}
{"step": 47000, "train_loss": 0.046562012284994125, "eval_loss": 0.03928022232139483}
{"step": 47500, "train_loss": 0.18221846222877502, "eval_loss": 0.04112485109362751}
{"step": 48000, "train_loss": 0.2040143460035324, "eval_loss": 0.038299327599816024}
{"step": 48500, "train_loss": 0.05132930353283882, "eval_loss": 0.04101442772662267}
{"step": 49000, "train_loss": 0.050885945558547974, "eval_loss": 0.03905782458605245}
{"step": 49500, "train_loss": 0.18245859444141388, "eval_loss": 0.039556460455060005}
{"step": 50000, "train_loss": 0.17213942110538483, "eval_loss": 0.03677181148668751}
{"step": 50500, "train_loss": 0.2221689075231552, "eval_loss": 0.039269302622415125}
{"step": 51000, "train_loss": 0.035095877945423126, "eval_loss": 0.03861914778826758}
{"step": 51500, "train_loss": 0.05516937002539635, "eval_loss": 0.0398446616018191}
{"step": 52000, "train_loss": 0.05715141445398331, "eval_loss": 0.037868452665861696}
{"step": 52500, "train_loss": 0.07831715792417526, "eval_loss": 0.04522049886872992}
{"step": 53000, "train_loss": 0.12778067588806152, "eval_loss": 0.040403085586149246}
{"step": 53500, "train_loss": 0.15970471501350403, "eval_loss": 0.03941528865834698}
{"step": 54000, "train_loss": 0.05161285772919655, "eval_loss": 0.038571860815864056}
{"step": 54500, "train_loss": 0.18574394285678864, "eval_loss": 0.03948824544204399}
{"step": 55000, "train_loss": 0.07045125216245651, "eval_loss": 0.03974881675094366}
{"step": 55500, "train_loss": 0.20432983338832855, "eval_loss": 0.038416021037846804}
{"step": 56000, "train_loss": 0.1905571073293686, "eval_loss": 0.0391716078738682}
{"step": 56500, "train_loss": 0.08130978047847748, "eval_loss": 0.03951523418072611}
{"step": 57000, "train_loss": 0.09699814021587372, "eval_loss": 0.04001188022084534}
{"step": 57500, "train_loss": 0.12123732268810272, "eval_loss": 0.03753187274560332}
{"step": 58000, "train_loss": 0.14924217760562897, "eval_loss": 0.037871034059207886}
{"step": 58500, "train_loss": 0.050268713384866714, "eval_loss": 0.03757714305538684}
{"step": 59000, "train_loss": 0.04151099920272827, "eval_loss": 0.03910046047531068}
{"step": 59500, "train_loss": 0.09491350501775742, "eval_loss": 0.039758675440680236}
{"step": 60000, "train_loss": 0.046820349991321564, "eval_loss": 0.03766027180245146}
{"step": 60500, "train_loss": 0.09066510200500488, "eval_loss": 0.03800374182173982}
{"step": 61000, "train_loss": 0.04007750004529953, "eval_loss": 0.039003095880616456}
{"step": 61500, "train_loss": 0.16525287926197052, "eval_loss": 0.03968040714971721}
{"step": 62000, "train_loss": 0.0869302973151207, "eval_loss": 0.0382875144132413}
{"step": 62500, "train_loss": 0.08638273179531097, "eval_loss": 0.03880476247286424}
{"step": 63000, "train_loss": 0.04319419339299202, "eval_loss": 0.03680556180188432}
{"step": 63500, "train_loss": 0.18857674300670624, "eval_loss": 0.0424469105200842}
{"step": 64000, "train_loss": 0.04880921170115471, "eval_loss": 0.038939845748245716}
{"step": 64500, "train_loss": 0.09509452432394028, "eval_loss": 0.03884190763346851}
{"step": 65000, "train_loss": 0.03625555709004402, "eval_loss": 0.03891512751579285}
{"step": 65500, "train_loss": 0.09135305881500244, "eval_loss": 0.040227463585324585}
{"step": 66000, "train_loss": 0.12290894985198975, "eval_loss": 0.03692335507366806}
{"step": 66500, "train_loss": 0.07020483165979385, "eval_loss": 0.038720632903277874}
{"step": 67000, "train_loss": 0.042012713849544525, "eval_loss": 0.03902384534012526}
{"step": 67500, "train_loss": 0.09481143951416016, "eval_loss": 0.03895178559469059}
{"step": 68000, "train_loss": 0.12616881728172302, "eval_loss": 0.03799475007690489}
{"step": 68500, "train_loss": 0.1950177699327469, "eval_loss": 0.038725285965483636}
{"step": 69000, "train_loss": 0.0439845472574234, "eval_loss": 0.03982500551501289}
{"step": 69500, "train_loss": 0.04375666007399559, "eval_loss": 0.03757060819771141}
{"step": 70000, "train_loss": 0.12172561883926392, "eval_loss": 0.040377029101364315}
{"step": 70500, "train_loss": 0.04144703224301338, "eval_loss": 0.040074685064610094}
{"step": 71000, "train_loss": 0.04834001883864403, "eval_loss": 0.04027873539598659}
{"step": 71500, "train_loss": 0.04859742894768715, "eval_loss": 0.03785321395844221}
{"step": 72000, "train_loss": 0.1756802350282669, "eval_loss": 0.038432400848250836}
{"step": 72500, "train_loss": 0.03470037877559662, "eval_loss": 0.03757508075796068}
{"step": 73000, "train_loss": 0.17244432866573334, "eval_loss": 0.03872086713090539}
{"step": 73500, "train_loss": 0.05057625472545624, "eval_loss": 0.03830234537599608}
{"step": 74000, "train_loss": 0.11695694178342819, "eval_loss": 0.03653866983950138}
{"step": 74500, "train_loss": 0.048680804669857025, "eval_loss": 0.03784315462689847}
{"step": 75000, "train_loss": 0.04072636365890503, "eval_loss": 0.041143623064272106}
{"step": 75500, "train_loss": 0.1291264444589615, "eval_loss": 0.03835269343107939}
{"step": 76000, "train_loss": 0.0455787368118763, "eval_loss": 0.03824232559418306}
{"step": 76500, "train_loss": 0.05121171474456787, "eval_loss": 0.038995058683212847}
{"step": 77000, "train_loss": 0.040676526725292206, "eval_loss": 0.04066471947589889}
{"step": 77500, "train_loss": 0.15351732075214386, "eval_loss": 0.038673129165545106}
{"step": 78000, "train_loss": 0.03737469017505646, "eval_loss": 0.03767394070746377}
{"step": 78500, "train_loss": 0.19297850131988525, "eval_loss": 0.038663953891955316}
{"step": 79000, "train_loss": 0.14422757923603058, "eval_loss": 0.03769676305819303}
{"step": 79500, "train_loss": 0.09701374918222427, "eval_loss": 0.037756070611067116}
{"step": 80000, "train_loss": 0.08385318517684937, "eval_loss": 0.03782333229901269}
{"step": 80500, "train_loss": 0.06771591305732727, "eval_loss": 0.040703217731788754}
{"step": 81000, "train_loss": 0.04327826946973801, "eval_loss": 0.03778424271149561}
{"step": 81500, "train_loss": 0.0464215911924839, "eval_loss": 0.038023478409741074}
{"step": 82000, "train_loss": 0.20413774251937866, "eval_loss": 0.038545841234736145}
{"step": 82500, "train_loss": 0.18952184915542603, "eval_loss": 0.0392796418746002}
{"step": 83000, "train_loss": 0.04651952162384987, "eval_loss": 0.038127955165691674}
{"step": 83500, "train_loss": 0.03934663534164429, "eval_loss": 0.038506762764882296}
{"step": 84000, "train_loss": 0.1861199587583542, "eval_loss": 0.03886867535766214}
{"step": 84500, "train_loss": 0.040964916348457336, "eval_loss": 0.03802930819801986}
{"step": 85000, "train_loss": 0.08406922221183777, "eval_loss": 0.03803543496178463}
{"step": 85500, "train_loss": 0.05550466477870941, "eval_loss": 0.03881758585339412}
{"step": 86000, "train_loss": 0.042176395654678345, "eval_loss": 0.0380725457216613}
{"step": 86500, "train_loss": 0.04349588230252266, "eval_loss": 0.039076593064237386}
{"step": 87000, "train_loss": 0.04346374422311783, "eval_loss": 0.037300335185136646}
{"step": 87500, "train_loss": 0.04188457131385803, "eval_loss": 0.03680864948546514}
{"step": 88000, "train_loss": 0.13103891909122467, "eval_loss": 0.03732777392724529}
{"step": 88500, "train_loss": 0.12641441822052002, "eval_loss": 0.03684842702932656}
{"step": 89000, "train_loss": 0.06719977408647537, "eval_loss": 0.03938451374415308}
{"step": 89500, "train_loss": 0.15994499623775482, "eval_loss": 0.0385720815975219}
{"step": 90000, "train_loss": 0.17999592423439026, "eval_loss": 0.03770284849451855}
{"step": 90500, "train_loss": 0.04300958290696144, "eval_loss": 0.03897161310305819}
{"step": 91000, "train_loss": 0.13476981222629547, "eval_loss": 0.03827337716938928}
{"step": 91500, "train_loss": 0.046468500047922134, "eval_loss": 0.039575239294208586}
{"step": 92000, "train_loss": 0.08047883957624435, "eval_loss": 0.03789208095986396}
{"step": 92500, "train_loss": 0.1281505972146988, "eval_loss": 0.037217154167592525}
{"step": 93000, "train_loss": 0.049832116812467575, "eval_loss": 0.03964303818065673}
{"step": 93500, "train_loss": 0.04742492735385895, "eval_loss": 0.03783304989337921}
{"step": 94000, "train_loss": 0.19372381269931793, "eval_loss": 0.037767282279673964}
{"step": 94500, "train_loss": 0.13911381363868713, "eval_loss": 0.039096895896364}
{"step": 95000, "train_loss": 0.13025957345962524, "eval_loss": 0.03787465253844857}
{"step": 95500, "train_loss": 0.04286036640405655, "eval_loss": 0.03844017587834969}
{"step": 96000, "train_loss": 0.15244902670383453, "eval_loss": 0.038063957123085856}
{"step": 96500, "train_loss": 0.21980270743370056, "eval_loss": 0.038171071966644377}
{"step": 97000, "train_loss": 0.07576228678226471, "eval_loss": 0.03820121759781614}
{"step": 97500, "train_loss": 0.1753600388765335, "eval_loss": 0.03860565385548398}
{"step": 98000, "train_loss": 0.039763193577528, "eval_loss": 0.03775921929627657}
{"step": 98500, "train_loss": 0.1857222020626068, "eval_loss": 0.038761893985792994}
{"step": 99000, "train_loss": 0.1818304806947708, "eval_loss": 0.03769975312752649}
{"step": 99500, "train_loss": 0.13084746897220612, "eval_loss": 0.040283499693032354}
{"step": 100000, "train_loss": 0.03792029619216919, "eval_loss": 0.03925448807422072}