ASD9987's picture
Add files using upload-large-folder tool
11d9a54 verified
Raw
History Blame Contribute Delete
55.6 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 1227,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002449479485609308,
"grad_norm": 25.491134643554688,
"learning_rate": 8.064516129032259e-08,
"loss": 1.924559235572815,
"step": 1,
"token_acc": 0.5780108634575764
},
{
"epoch": 0.01224739742804654,
"grad_norm": 25.177900314331055,
"learning_rate": 4.032258064516129e-07,
"loss": 1.9293854236602783,
"step": 5,
"token_acc": 0.5720852260436946
},
{
"epoch": 0.02449479485609308,
"grad_norm": 21.1153621673584,
"learning_rate": 8.064516129032258e-07,
"loss": 1.91040096282959,
"step": 10,
"token_acc": 0.5713233701537795
},
{
"epoch": 0.03674219228413962,
"grad_norm": 12.280715942382812,
"learning_rate": 1.2096774193548388e-06,
"loss": 1.7182601928710937,
"step": 15,
"token_acc": 0.586717964412189
},
{
"epoch": 0.04898958971218616,
"grad_norm": 6.550159454345703,
"learning_rate": 1.6129032258064516e-06,
"loss": 1.5319179534912108,
"step": 20,
"token_acc": 0.6047231408462648
},
{
"epoch": 0.0612369871402327,
"grad_norm": 6.581821441650391,
"learning_rate": 2.0161290322580646e-06,
"loss": 1.466599464416504,
"step": 25,
"token_acc": 0.6147400745777583
},
{
"epoch": 0.07348438456827924,
"grad_norm": 5.92696475982666,
"learning_rate": 2.4193548387096776e-06,
"loss": 1.3790240287780762,
"step": 30,
"token_acc": 0.635921709095561
},
{
"epoch": 0.08573178199632578,
"grad_norm": 5.390381336212158,
"learning_rate": 2.822580645161291e-06,
"loss": 1.3392158508300782,
"step": 35,
"token_acc": 0.6405231675743237
},
{
"epoch": 0.09797917942437231,
"grad_norm": 4.956661701202393,
"learning_rate": 3.225806451612903e-06,
"loss": 1.3219813346862792,
"step": 40,
"token_acc": 0.6484368119771026
},
{
"epoch": 0.11022657685241886,
"grad_norm": 4.720174789428711,
"learning_rate": 3.6290322580645166e-06,
"loss": 1.2559122085571288,
"step": 45,
"token_acc": 0.6555207244862418
},
{
"epoch": 0.1224739742804654,
"grad_norm": 4.8690924644470215,
"learning_rate": 4.032258064516129e-06,
"loss": 1.255866241455078,
"step": 50,
"token_acc": 0.6545439238961148
},
{
"epoch": 0.13472137170851195,
"grad_norm": 5.002169132232666,
"learning_rate": 4.435483870967742e-06,
"loss": 1.2084766387939454,
"step": 55,
"token_acc": 0.6650250599259098
},
{
"epoch": 0.14696876913655849,
"grad_norm": 5.190518856048584,
"learning_rate": 4.838709677419355e-06,
"loss": 1.2049914360046388,
"step": 60,
"token_acc": 0.6654315136369512
},
{
"epoch": 0.15921616656460502,
"grad_norm": 4.761566162109375,
"learning_rate": 4.999918191571812e-06,
"loss": 1.2158527374267578,
"step": 65,
"token_acc": 0.6622983434972536
},
{
"epoch": 0.17146356399265156,
"grad_norm": 4.52225923538208,
"learning_rate": 4.999418270566514e-06,
"loss": 1.194795799255371,
"step": 70,
"token_acc": 0.6693687707641196
},
{
"epoch": 0.1837109614206981,
"grad_norm": 4.82882833480835,
"learning_rate": 4.99846396845553e-06,
"loss": 1.1578558921813964,
"step": 75,
"token_acc": 0.6726437976437977
},
{
"epoch": 0.19595835884874463,
"grad_norm": 4.834425449371338,
"learning_rate": 4.9970554587259724e-06,
"loss": 1.1812004089355468,
"step": 80,
"token_acc": 0.6710710795768364
},
{
"epoch": 0.2082057562767912,
"grad_norm": 4.780599117279053,
"learning_rate": 4.995192997437504e-06,
"loss": 1.1845964431762694,
"step": 85,
"token_acc": 0.6682505029750438
},
{
"epoch": 0.22045315370483773,
"grad_norm": 4.873416900634766,
"learning_rate": 4.992876923175802e-06,
"loss": 1.1632291793823242,
"step": 90,
"token_acc": 0.6756803605477553
},
{
"epoch": 0.23270055113288426,
"grad_norm": 4.529237747192383,
"learning_rate": 4.990107656990993e-06,
"loss": 1.1902219772338867,
"step": 95,
"token_acc": 0.6641645462256149
},
{
"epoch": 0.2449479485609308,
"grad_norm": 4.760631561279297,
"learning_rate": 4.986885702321115e-06,
"loss": 1.1730481147766114,
"step": 100,
"token_acc": 0.6734773895617322
},
{
"epoch": 0.25719534598897736,
"grad_norm": 4.880444526672363,
"learning_rate": 4.983211644900594e-06,
"loss": 1.1414649963378907,
"step": 105,
"token_acc": 0.6766537619929305
},
{
"epoch": 0.2694427434170239,
"grad_norm": 5.00352668762207,
"learning_rate": 4.9790861526537596e-06,
"loss": 1.1441005706787108,
"step": 110,
"token_acc": 0.6751783539237863
},
{
"epoch": 0.28169014084507044,
"grad_norm": 4.820106506347656,
"learning_rate": 4.974509975573422e-06,
"loss": 1.0909159660339356,
"step": 115,
"token_acc": 0.6871750433275563
},
{
"epoch": 0.29393753827311697,
"grad_norm": 4.789821147918701,
"learning_rate": 4.9694839455845215e-06,
"loss": 1.1449825286865234,
"step": 120,
"token_acc": 0.6781117696867062
},
{
"epoch": 0.3061849357011635,
"grad_norm": 4.367542266845703,
"learning_rate": 4.964008976392897e-06,
"loss": 1.134037971496582,
"step": 125,
"token_acc": 0.6795124037639008
},
{
"epoch": 0.31843233312921004,
"grad_norm": 4.4926228523254395,
"learning_rate": 4.958086063319172e-06,
"loss": 1.1610729217529296,
"step": 130,
"token_acc": 0.673144422566561
},
{
"epoch": 0.3306797305572566,
"grad_norm": 4.444128036499023,
"learning_rate": 4.951716283117817e-06,
"loss": 1.1206705093383789,
"step": 135,
"token_acc": 0.6836945087313275
},
{
"epoch": 0.3429271279853031,
"grad_norm": 4.744080543518066,
"learning_rate": 4.944900793781394e-06,
"loss": 1.0989964485168457,
"step": 140,
"token_acc": 0.6864965720732448
},
{
"epoch": 0.35517452541334965,
"grad_norm": 4.457662105560303,
"learning_rate": 4.937640834330046e-06,
"loss": 1.1248577117919922,
"step": 145,
"token_acc": 0.6802127482755755
},
{
"epoch": 0.3674219228413962,
"grad_norm": 4.734897136688232,
"learning_rate": 4.929937724586244e-06,
"loss": 1.1136582374572754,
"step": 150,
"token_acc": 0.6833733493397359
},
{
"epoch": 0.3796693202694427,
"grad_norm": 4.869287967681885,
"learning_rate": 4.921792864934858e-06,
"loss": 1.1292306900024414,
"step": 155,
"token_acc": 0.6792193276588427
},
{
"epoch": 0.39191671769748926,
"grad_norm": 4.528173446655273,
"learning_rate": 4.913207736068565e-06,
"loss": 1.1377950668334962,
"step": 160,
"token_acc": 0.6737299063010401
},
{
"epoch": 0.40416411512553585,
"grad_norm": 4.269668102264404,
"learning_rate": 4.904183898718672e-06,
"loss": 1.1122922897338867,
"step": 165,
"token_acc": 0.680643921602118
},
{
"epoch": 0.4164115125535824,
"grad_norm": 4.381101608276367,
"learning_rate": 4.894722993371386e-06,
"loss": 1.1267989158630372,
"step": 170,
"token_acc": 0.6811408357284988
},
{
"epoch": 0.4286589099816289,
"grad_norm": 4.162039279937744,
"learning_rate": 4.884826739969575e-06,
"loss": 1.0866413116455078,
"step": 175,
"token_acc": 0.6864225548815083
},
{
"epoch": 0.44090630740967546,
"grad_norm": 4.414100646972656,
"learning_rate": 4.8744969376000965e-06,
"loss": 1.0925677299499512,
"step": 180,
"token_acc": 0.6853174429303772
},
{
"epoch": 0.453153704837722,
"grad_norm": 4.161582946777344,
"learning_rate": 4.863735464166733e-06,
"loss": 1.076032543182373,
"step": 185,
"token_acc": 0.6925150583378965
},
{
"epoch": 0.46540110226576853,
"grad_norm": 4.268298149108887,
"learning_rate": 4.8525442760487965e-06,
"loss": 1.0737590789794922,
"step": 190,
"token_acc": 0.6904064904650384
},
{
"epoch": 0.47764849969381507,
"grad_norm": 4.538225173950195,
"learning_rate": 4.840925407745471e-06,
"loss": 1.0695731163024902,
"step": 195,
"token_acc": 0.6943261795116865
},
{
"epoch": 0.4898958971218616,
"grad_norm": 4.845300197601318,
"learning_rate": 4.828880971505951e-06,
"loss": 1.0848728179931642,
"step": 200,
"token_acc": 0.6878200751109593
},
{
"epoch": 0.5021432945499081,
"grad_norm": 4.483066082000732,
"learning_rate": 4.816413156945441e-06,
"loss": 1.05485258102417,
"step": 205,
"token_acc": 0.6907351592189752
},
{
"epoch": 0.5143906919779547,
"grad_norm": 4.387731075286865,
"learning_rate": 4.803524230647105e-06,
"loss": 1.105961227416992,
"step": 210,
"token_acc": 0.6852805165343339
},
{
"epoch": 0.5266380894060012,
"grad_norm": 4.123055934906006,
"learning_rate": 4.790216535750006e-06,
"loss": 1.0644481658935547,
"step": 215,
"token_acc": 0.6933047210300429
},
{
"epoch": 0.5388854868340478,
"grad_norm": 4.534999847412109,
"learning_rate": 4.776492491523135e-06,
"loss": 1.0861276626586913,
"step": 220,
"token_acc": 0.6874918876822568
},
{
"epoch": 0.5511328842620943,
"grad_norm": 4.581034183502197,
"learning_rate": 4.7623545929256045e-06,
"loss": 1.0731281280517577,
"step": 225,
"token_acc": 0.6880664315371222
},
{
"epoch": 0.5633802816901409,
"grad_norm": 4.256408214569092,
"learning_rate": 4.747805410153077e-06,
"loss": 1.0644266128540039,
"step": 230,
"token_acc": 0.6951384199864956
},
{
"epoch": 0.5756276791181874,
"grad_norm": 4.496469020843506,
"learning_rate": 4.7328475881705154e-06,
"loss": 1.0836721420288087,
"step": 235,
"token_acc": 0.6864257097316159
},
{
"epoch": 0.5878750765462339,
"grad_norm": 4.387855052947998,
"learning_rate": 4.717483846231345e-06,
"loss": 1.0642669677734375,
"step": 240,
"token_acc": 0.6920529801324503
},
{
"epoch": 0.6001224739742804,
"grad_norm": 4.229402542114258,
"learning_rate": 4.701716977383105e-06,
"loss": 1.0778236389160156,
"step": 245,
"token_acc": 0.690152910438172
},
{
"epoch": 0.612369871402327,
"grad_norm": 4.210731506347656,
"learning_rate": 4.685549847959687e-06,
"loss": 1.0763225555419922,
"step": 250,
"token_acc": 0.6940343869399097
},
{
"epoch": 0.6246172688303735,
"grad_norm": 4.474976062774658,
"learning_rate": 4.668985397060254e-06,
"loss": 1.0442864418029785,
"step": 255,
"token_acc": 0.6958573675930781
},
{
"epoch": 0.6368646662584201,
"grad_norm": 4.396641731262207,
"learning_rate": 4.6520266360149215e-06,
"loss": 1.0383359909057617,
"step": 260,
"token_acc": 0.6999231557377049
},
{
"epoch": 0.6491120636864667,
"grad_norm": 4.332795143127441,
"learning_rate": 4.63467664783732e-06,
"loss": 1.0636303901672364,
"step": 265,
"token_acc": 0.6920557608330534
},
{
"epoch": 0.6613594611145132,
"grad_norm": 4.259671688079834,
"learning_rate": 4.6169385866641185e-06,
"loss": 1.0785508155822754,
"step": 270,
"token_acc": 0.688282819646903
},
{
"epoch": 0.6736068585425597,
"grad_norm": 4.390286922454834,
"learning_rate": 4.59881567718161e-06,
"loss": 1.0762375831604003,
"step": 275,
"token_acc": 0.6903123117955777
},
{
"epoch": 0.6858542559706062,
"grad_norm": 4.433945178985596,
"learning_rate": 4.580311214039495e-06,
"loss": 1.0589970588684081,
"step": 280,
"token_acc": 0.696341250436605
},
{
"epoch": 0.6981016533986528,
"grad_norm": 4.147647857666016,
"learning_rate": 4.561428561251919e-06,
"loss": 1.0467605590820312,
"step": 285,
"token_acc": 0.6951623873490903
},
{
"epoch": 0.7103490508266993,
"grad_norm": 4.678038597106934,
"learning_rate": 4.542171151585921e-06,
"loss": 1.0295079231262207,
"step": 290,
"token_acc": 0.6962863573407202
},
{
"epoch": 0.7225964482547459,
"grad_norm": 4.077085494995117,
"learning_rate": 4.522542485937369e-06,
"loss": 1.0482128143310547,
"step": 295,
"token_acc": 0.6943261496107025
},
{
"epoch": 0.7348438456827924,
"grad_norm": 4.4850311279296875,
"learning_rate": 4.502546132694518e-06,
"loss": 1.0553340911865234,
"step": 300,
"token_acc": 0.6946087400536147
},
{
"epoch": 0.747091243110839,
"grad_norm": 4.3874945640563965,
"learning_rate": 4.482185727089293e-06,
"loss": 1.0559030532836915,
"step": 305,
"token_acc": 0.6942511741172378
},
{
"epoch": 0.7593386405388854,
"grad_norm": 4.1652445793151855,
"learning_rate": 4.4614649705364295e-06,
"loss": 1.0298480987548828,
"step": 310,
"token_acc": 0.6981648138344804
},
{
"epoch": 0.771586037966932,
"grad_norm": 4.22780179977417,
"learning_rate": 4.440387629960568e-06,
"loss": 1.0484783172607421,
"step": 315,
"token_acc": 0.6957631444614599
},
{
"epoch": 0.7838334353949785,
"grad_norm": 4.2819743156433105,
"learning_rate": 4.418957537111453e-06,
"loss": 1.0649592399597168,
"step": 320,
"token_acc": 0.6907533788304563
},
{
"epoch": 0.7960808328230251,
"grad_norm": 4.22964334487915,
"learning_rate": 4.397178587867335e-06,
"loss": 1.0299952507019043,
"step": 325,
"token_acc": 0.7027920179638182
},
{
"epoch": 0.8083282302510717,
"grad_norm": 4.2118072509765625,
"learning_rate": 4.375054741526726e-06,
"loss": 1.0265492439270019,
"step": 330,
"token_acc": 0.7014073629108384
},
{
"epoch": 0.8205756276791182,
"grad_norm": 4.578775405883789,
"learning_rate": 4.352590020088617e-06,
"loss": 1.0408875465393066,
"step": 335,
"token_acc": 0.6972135427813209
},
{
"epoch": 0.8328230251071648,
"grad_norm": 4.428823471069336,
"learning_rate": 4.3297885075213e-06,
"loss": 1.042294979095459,
"step": 340,
"token_acc": 0.6945207215580246
},
{
"epoch": 0.8450704225352113,
"grad_norm": 4.292690277099609,
"learning_rate": 4.306654349019925e-06,
"loss": 1.0228508949279784,
"step": 345,
"token_acc": 0.7027719642933413
},
{
"epoch": 0.8573178199632578,
"grad_norm": 4.429483413696289,
"learning_rate": 4.283191750252923e-06,
"loss": 1.016273593902588,
"step": 350,
"token_acc": 0.7025961368066631
},
{
"epoch": 0.8695652173913043,
"grad_norm": 4.146049976348877,
"learning_rate": 4.259404976597442e-06,
"loss": 1.020415687561035,
"step": 355,
"token_acc": 0.7038205397826849
},
{
"epoch": 0.8818126148193509,
"grad_norm": 4.339040756225586,
"learning_rate": 4.2352983523639166e-06,
"loss": 1.0303951263427735,
"step": 360,
"token_acc": 0.6992072681927496
},
{
"epoch": 0.8940600122473974,
"grad_norm": 4.005756855010986,
"learning_rate": 4.21087626000994e-06,
"loss": 1.0201931953430177,
"step": 365,
"token_acc": 0.6991914198332565
},
{
"epoch": 0.906307409675444,
"grad_norm": 4.079517841339111,
"learning_rate": 4.186143139343549e-06,
"loss": 1.0360610961914063,
"step": 370,
"token_acc": 0.6990502744619674
},
{
"epoch": 0.9185548071034905,
"grad_norm": 4.114217758178711,
"learning_rate": 4.161103486716095e-06,
"loss": 1.0459300994873046,
"step": 375,
"token_acc": 0.6947196842963154
},
{
"epoch": 0.9308022045315371,
"grad_norm": 4.301392078399658,
"learning_rate": 4.135761854204825e-06,
"loss": 1.042283821105957,
"step": 380,
"token_acc": 0.6957355890817127
},
{
"epoch": 0.9430496019595835,
"grad_norm": 4.037268161773682,
"learning_rate": 4.1101228487853475e-06,
"loss": 1.012284278869629,
"step": 385,
"token_acc": 0.7043765837735687
},
{
"epoch": 0.9552969993876301,
"grad_norm": 4.39351224899292,
"learning_rate": 4.084191131494097e-06,
"loss": 1.0354315757751464,
"step": 390,
"token_acc": 0.6978448462772646
},
{
"epoch": 0.9675443968156767,
"grad_norm": 4.0855913162231445,
"learning_rate": 4.057971416580992e-06,
"loss": 1.0271640777587892,
"step": 395,
"token_acc": 0.7002642506606267
},
{
"epoch": 0.9797917942437232,
"grad_norm": 4.416122913360596,
"learning_rate": 4.0314684706524056e-06,
"loss": 1.0156761169433595,
"step": 400,
"token_acc": 0.7043797253165123
},
{
"epoch": 0.9920391916717698,
"grad_norm": 4.202881813049316,
"learning_rate": 4.004687111804616e-06,
"loss": 1.0171480178833008,
"step": 405,
"token_acc": 0.6982854218203531
},
{
"epoch": 1.0024494794856094,
"grad_norm": 4.206028461456299,
"learning_rate": 3.977632208747911e-06,
"loss": 1.0142362594604493,
"step": 410,
"token_acc": 0.711591819956839
},
{
"epoch": 1.014696876913656,
"grad_norm": 4.478796005249023,
"learning_rate": 3.950308679921478e-06,
"loss": 0.7849956512451172,
"step": 415,
"token_acc": 0.7602984679235286
},
{
"epoch": 1.0269442743417023,
"grad_norm": 4.66928768157959,
"learning_rate": 3.922721492599255e-06,
"loss": 0.8031488418579101,
"step": 420,
"token_acc": 0.7535921080849238
},
{
"epoch": 1.039191671769749,
"grad_norm": 4.528433322906494,
"learning_rate": 3.894875661986912e-06,
"loss": 0.7838258743286133,
"step": 425,
"token_acc": 0.7596577540106952
},
{
"epoch": 1.0514390691977955,
"grad_norm": 4.277143478393555,
"learning_rate": 3.866776250310107e-06,
"loss": 0.7442241668701172,
"step": 430,
"token_acc": 0.769938520245919
},
{
"epoch": 1.063686466625842,
"grad_norm": 4.469383239746094,
"learning_rate": 3.838428365894205e-06,
"loss": 0.7771434783935547,
"step": 435,
"token_acc": 0.7569792872764698
},
{
"epoch": 1.0759338640538885,
"grad_norm": 4.6610307693481445,
"learning_rate": 3.8098371622356067e-06,
"loss": 0.770506477355957,
"step": 440,
"token_acc": 0.7596531343026015
},
{
"epoch": 1.088181261481935,
"grad_norm": 4.738448619842529,
"learning_rate": 3.781007837064875e-06,
"loss": 0.7778576850891114,
"step": 445,
"token_acc": 0.7555954979244234
},
{
"epoch": 1.1004286589099816,
"grad_norm": 4.395505905151367,
"learning_rate": 3.7519456314018105e-06,
"loss": 0.7623329162597656,
"step": 450,
"token_acc": 0.76318975955717
},
{
"epoch": 1.1126760563380282,
"grad_norm": 4.638436794281006,
"learning_rate": 3.7226558286026633e-06,
"loss": 0.7792695999145508,
"step": 455,
"token_acc": 0.7576679120688157
},
{
"epoch": 1.1249234537660746,
"grad_norm": 4.638317108154297,
"learning_rate": 3.6931437533996484e-06,
"loss": 0.7715627670288085,
"step": 460,
"token_acc": 0.7627607634265424
},
{
"epoch": 1.1371708511941212,
"grad_norm": 4.232605457305908,
"learning_rate": 3.663414770932933e-06,
"loss": 0.8004587173461915,
"step": 465,
"token_acc": 0.7536386529514704
},
{
"epoch": 1.1494182486221678,
"grad_norm": 4.363043785095215,
"learning_rate": 3.6334742857752882e-06,
"loss": 0.7820894241333007,
"step": 470,
"token_acc": 0.7588262457495487
},
{
"epoch": 1.1616656460502144,
"grad_norm": 4.640029430389404,
"learning_rate": 3.603327740949559e-06,
"loss": 0.785007905960083,
"step": 475,
"token_acc": 0.7590175858970519
},
{
"epoch": 1.1739130434782608,
"grad_norm": 4.586259841918945,
"learning_rate": 3.572980616939159e-06,
"loss": 0.7841495513916016,
"step": 480,
"token_acc": 0.7581941867656153
},
{
"epoch": 1.1861604409063073,
"grad_norm": 4.2993974685668945,
"learning_rate": 3.5424384306917392e-06,
"loss": 0.7778982162475586,
"step": 485,
"token_acc": 0.7567601612361438
},
{
"epoch": 1.198407838334354,
"grad_norm": 4.595414638519287,
"learning_rate": 3.511706734616244e-06,
"loss": 0.7634652137756348,
"step": 490,
"token_acc": 0.7619796444327961
},
{
"epoch": 1.2106552357624005,
"grad_norm": 4.509241580963135,
"learning_rate": 3.480791115573506e-06,
"loss": 0.7961736679077148,
"step": 495,
"token_acc": 0.7543197965090781
},
{
"epoch": 1.2229026331904471,
"grad_norm": 4.559839248657227,
"learning_rate": 3.4496971938605877e-06,
"loss": 0.7862816333770752,
"step": 500,
"token_acc": 0.7570439402517093
},
{
"epoch": 1.2351500306184935,
"grad_norm": 4.518557071685791,
"learning_rate": 3.41843062218904e-06,
"loss": 0.7893893241882324,
"step": 505,
"token_acc": 0.7577525330058336
},
{
"epoch": 1.24739742804654,
"grad_norm": 4.483558177947998,
"learning_rate": 3.3869970846572687e-06,
"loss": 0.751371431350708,
"step": 510,
"token_acc": 0.7688727583262169
},
{
"epoch": 1.2596448254745867,
"grad_norm": 4.576009750366211,
"learning_rate": 3.3554022957171956e-06,
"loss": 0.7810420989990234,
"step": 515,
"token_acc": 0.7609458556149733
},
{
"epoch": 1.2718922229026333,
"grad_norm": 4.48703145980835,
"learning_rate": 3.3236519991354e-06,
"loss": 0.7708640575408936,
"step": 520,
"token_acc": 0.7627451818298363
},
{
"epoch": 1.2841396203306799,
"grad_norm": 4.633534908294678,
"learning_rate": 3.2917519669489344e-06,
"loss": 0.7879925727844238,
"step": 525,
"token_acc": 0.7564777843853538
},
{
"epoch": 1.2963870177587262,
"grad_norm": 4.27849817276001,
"learning_rate": 3.259707998415998e-06,
"loss": 0.7592859268188477,
"step": 530,
"token_acc": 0.7669673539518901
},
{
"epoch": 1.3086344151867728,
"grad_norm": 4.644284725189209,
"learning_rate": 3.227525918961659e-06,
"loss": 0.7553563594818116,
"step": 535,
"token_acc": 0.7627184132572017
},
{
"epoch": 1.3208818126148194,
"grad_norm": 4.641902923583984,
"learning_rate": 3.195211579118828e-06,
"loss": 0.7935165882110595,
"step": 540,
"token_acc": 0.750185549006767
},
{
"epoch": 1.3331292100428658,
"grad_norm": 4.571802616119385,
"learning_rate": 3.1627708534646552e-06,
"loss": 0.7627959251403809,
"step": 545,
"token_acc": 0.760615279146493
},
{
"epoch": 1.3453766074709124,
"grad_norm": 4.525778770446777,
"learning_rate": 3.1302096395525726e-06,
"loss": 0.7925759315490722,
"step": 550,
"token_acc": 0.7539050733680451
},
{
"epoch": 1.357624004898959,
"grad_norm": 4.676870822906494,
"learning_rate": 3.0975338568401385e-06,
"loss": 0.7834089279174805,
"step": 555,
"token_acc": 0.7570494217525015
},
{
"epoch": 1.3698714023270055,
"grad_norm": 4.788694858551025,
"learning_rate": 3.0647494456129217e-06,
"loss": 0.7911327362060547,
"step": 560,
"token_acc": 0.7593526134253118
},
{
"epoch": 1.3821187997550521,
"grad_norm": 4.444942951202393,
"learning_rate": 3.031862365904581e-06,
"loss": 0.7835145950317383,
"step": 565,
"token_acc": 0.7584673280875812
},
{
"epoch": 1.3943661971830985,
"grad_norm": 4.622507572174072,
"learning_rate": 2.9988785964133665e-06,
"loss": 0.8062938690185547,
"step": 570,
"token_acc": 0.7515983292131958
},
{
"epoch": 1.406613594611145,
"grad_norm": 4.62219762802124,
"learning_rate": 2.9658041334152233e-06,
"loss": 0.7802319049835205,
"step": 575,
"token_acc": 0.7562575522181944
},
{
"epoch": 1.4188609920391917,
"grad_norm": 4.535560607910156,
"learning_rate": 2.9326449896736975e-06,
"loss": 0.7671322822570801,
"step": 580,
"token_acc": 0.7597468243154147
},
{
"epoch": 1.4311083894672383,
"grad_norm": 4.481744289398193,
"learning_rate": 2.8994071933468527e-06,
"loss": 0.770707654953003,
"step": 585,
"token_acc": 0.7620617841027421
},
{
"epoch": 1.4433557868952849,
"grad_norm": 4.622373104095459,
"learning_rate": 2.8660967868913747e-06,
"loss": 0.7583498954772949,
"step": 590,
"token_acc": 0.7615316901408451
},
{
"epoch": 1.4556031843233312,
"grad_norm": 4.665287971496582,
"learning_rate": 2.832719825964093e-06,
"loss": 0.7807941436767578,
"step": 595,
"token_acc": 0.7575496898628152
},
{
"epoch": 1.4678505817513778,
"grad_norm": 4.833719730377197,
"learning_rate": 2.7992823783210893e-06,
"loss": 0.7652729988098145,
"step": 600,
"token_acc": 0.7592282618271518
},
{
"epoch": 1.4800979791794244,
"grad_norm": 4.617916584014893,
"learning_rate": 2.76579052271461e-06,
"loss": 0.7893416881561279,
"step": 605,
"token_acc": 0.7561697515424379
},
{
"epoch": 1.4923453766074708,
"grad_norm": 4.6830573081970215,
"learning_rate": 2.732250347787986e-06,
"loss": 0.7839091300964356,
"step": 610,
"token_acc": 0.7619602260471938
},
{
"epoch": 1.5045927740355176,
"grad_norm": 4.605529308319092,
"learning_rate": 2.6986679509687457e-06,
"loss": 0.7774672031402587,
"step": 615,
"token_acc": 0.7564693825262618
},
{
"epoch": 1.516840171463564,
"grad_norm": 4.6576972007751465,
"learning_rate": 2.6650494373601355e-06,
"loss": 0.7678401947021485,
"step": 620,
"token_acc": 0.7609700258617035
},
{
"epoch": 1.5290875688916106,
"grad_norm": 4.614404678344727,
"learning_rate": 2.6314009186312437e-06,
"loss": 0.7846922874450684,
"step": 625,
"token_acc": 0.7573959445037354
},
{
"epoch": 1.5413349663196572,
"grad_norm": 4.3292646408081055,
"learning_rate": 2.5977285119059347e-06,
"loss": 0.7860712051391602,
"step": 630,
"token_acc": 0.7572753573859768
},
{
"epoch": 1.5535823637477035,
"grad_norm": 4.779139518737793,
"learning_rate": 2.5640383386507812e-06,
"loss": 0.788635540008545,
"step": 635,
"token_acc": 0.7597786927431807
},
{
"epoch": 1.5658297611757501,
"grad_norm": 4.66672420501709,
"learning_rate": 2.53033652356222e-06,
"loss": 0.7763586521148682,
"step": 640,
"token_acc": 0.7580442051326588
},
{
"epoch": 1.5780771586037967,
"grad_norm": 4.4589080810546875,
"learning_rate": 2.4966291934531112e-06,
"loss": 0.7758882999420166,
"step": 645,
"token_acc": 0.7591176839202908
},
{
"epoch": 1.590324556031843,
"grad_norm": 4.580643177032471,
"learning_rate": 2.462922476138918e-06,
"loss": 0.7874266624450683,
"step": 650,
"token_acc": 0.7575214601216768
},
{
"epoch": 1.60257195345989,
"grad_norm": 4.907217502593994,
"learning_rate": 2.429222499323698e-06,
"loss": 0.7663785934448242,
"step": 655,
"token_acc": 0.7602286786978967
},
{
"epoch": 1.6148193508879363,
"grad_norm": 4.910719394683838,
"learning_rate": 2.3955353894861234e-06,
"loss": 0.787629222869873,
"step": 660,
"token_acc": 0.7607565631415717
},
{
"epoch": 1.6270667483159829,
"grad_norm": 4.778140544891357,
"learning_rate": 2.3618672707657176e-06,
"loss": 0.7681752681732178,
"step": 665,
"token_acc": 0.7612144537096429
},
{
"epoch": 1.6393141457440294,
"grad_norm": 4.5776214599609375,
"learning_rate": 2.328224263849518e-06,
"loss": 0.7675065517425537,
"step": 670,
"token_acc": 0.762601201358057
},
{
"epoch": 1.6515615431720758,
"grad_norm": 4.621997356414795,
"learning_rate": 2.2946124848593695e-06,
"loss": 0.7452384948730468,
"step": 675,
"token_acc": 0.7706269943226555
},
{
"epoch": 1.6638089406001226,
"grad_norm": 4.933689117431641,
"learning_rate": 2.261038044240042e-06,
"loss": 0.7669482707977295,
"step": 680,
"token_acc": 0.7602354366831127
},
{
"epoch": 1.676056338028169,
"grad_norm": 4.68771505355835,
"learning_rate": 2.2275070456483862e-06,
"loss": 0.7899266242980957,
"step": 685,
"token_acc": 0.7548017807928769
},
{
"epoch": 1.6883037354562156,
"grad_norm": 4.409292697906494,
"learning_rate": 2.1940255848437216e-06,
"loss": 0.7827797412872315,
"step": 690,
"token_acc": 0.7585512216030862
},
{
"epoch": 1.7005511328842622,
"grad_norm": 4.816332817077637,
"learning_rate": 2.160599748579658e-06,
"loss": 0.7791535377502441,
"step": 695,
"token_acc": 0.7603298457173258
},
{
"epoch": 1.7127985303123086,
"grad_norm": 4.967842102050781,
"learning_rate": 2.127235613497556e-06,
"loss": 0.762655782699585,
"step": 700,
"token_acc": 0.7650328227571116
},
{
"epoch": 1.7250459277403551,
"grad_norm": 4.628602981567383,
"learning_rate": 2.093939245021826e-06,
"loss": 0.7575776100158691,
"step": 705,
"token_acc": 0.7649840199640996
},
{
"epoch": 1.7372933251684017,
"grad_norm": 4.693065166473389,
"learning_rate": 2.060716696257262e-06,
"loss": 0.7696513175964356,
"step": 710,
"token_acc": 0.7597179452849556
},
{
"epoch": 1.749540722596448,
"grad_norm": 4.693673610687256,
"learning_rate": 2.0275740068886293e-06,
"loss": 0.7588753700256348,
"step": 715,
"token_acc": 0.7656597358441218
},
{
"epoch": 1.761788120024495,
"grad_norm": 4.765112400054932,
"learning_rate": 1.9945172020826696e-06,
"loss": 0.7718194007873536,
"step": 720,
"token_acc": 0.763516141579152
},
{
"epoch": 1.7740355174525413,
"grad_norm": 4.737748622894287,
"learning_rate": 1.961552291392763e-06,
"loss": 0.7587370872497559,
"step": 725,
"token_acc": 0.7637926610212984
},
{
"epoch": 1.7862829148805879,
"grad_norm": 4.706098556518555,
"learning_rate": 1.9286852676664234e-06,
"loss": 0.7728893280029296,
"step": 730,
"token_acc": 0.7610371408549405
},
{
"epoch": 1.7985303123086345,
"grad_norm": 4.600115776062012,
"learning_rate": 1.8959221059558286e-06,
"loss": 0.7641496658325195,
"step": 735,
"token_acc": 0.7624657653349564
},
{
"epoch": 1.8107777097366808,
"grad_norm": 4.760969161987305,
"learning_rate": 1.8632687624315885e-06,
"loss": 0.7687458038330078,
"step": 740,
"token_acc": 0.7615896922474209
},
{
"epoch": 1.8230251071647277,
"grad_norm": 4.521633148193359,
"learning_rate": 1.8307311732999433e-06,
"loss": 0.7207860469818115,
"step": 745,
"token_acc": 0.7736193122612018
},
{
"epoch": 1.835272504592774,
"grad_norm": 4.4776201248168945,
"learning_rate": 1.798315253723593e-06,
"loss": 0.7585281372070313,
"step": 750,
"token_acc": 0.7653171215452939
},
{
"epoch": 1.8475199020208206,
"grad_norm": 4.7328200340271,
"learning_rate": 1.7660268967463515e-06,
"loss": 0.7706717491149903,
"step": 755,
"token_acc": 0.7584294199860238
},
{
"epoch": 1.8597672994488672,
"grad_norm": 4.588700771331787,
"learning_rate": 1.733871972221824e-06,
"loss": 0.772399616241455,
"step": 760,
"token_acc": 0.7600653117346281
},
{
"epoch": 1.8720146968769136,
"grad_norm": 4.575390815734863,
"learning_rate": 1.7018563257462956e-06,
"loss": 0.7517253398895264,
"step": 765,
"token_acc": 0.7683217139942187
},
{
"epoch": 1.8842620943049602,
"grad_norm": 4.6710429191589355,
"learning_rate": 1.6699857775960343e-06,
"loss": 0.7637727737426758,
"step": 770,
"token_acc": 0.7610989010989011
},
{
"epoch": 1.8965094917330068,
"grad_norm": 4.554412841796875,
"learning_rate": 1.6382661216691968e-06,
"loss": 0.7537057399749756,
"step": 775,
"token_acc": 0.7649308240955572
},
{
"epoch": 1.9087568891610531,
"grad_norm": 4.810478210449219,
"learning_rate": 1.606703124432522e-06,
"loss": 0.7450632572174072,
"step": 780,
"token_acc": 0.7677834064109659
},
{
"epoch": 1.9210042865891,
"grad_norm": 4.840790748596191,
"learning_rate": 1.5753025238730294e-06,
"loss": 0.7469035148620605,
"step": 785,
"token_acc": 0.7657027682941878
},
{
"epoch": 1.9332516840171463,
"grad_norm": 4.550791263580322,
"learning_rate": 1.5440700284548708e-06,
"loss": 0.7843441963195801,
"step": 790,
"token_acc": 0.7550630492930837
},
{
"epoch": 1.945499081445193,
"grad_norm": 4.960586071014404,
"learning_rate": 1.513011316081567e-06,
"loss": 0.7551403522491456,
"step": 795,
"token_acc": 0.7668317041174728
},
{
"epoch": 1.9577464788732395,
"grad_norm": 4.711572647094727,
"learning_rate": 1.4821320330637962e-06,
"loss": 0.7480823040008545,
"step": 800,
"token_acc": 0.7650656902864528
},
{
"epoch": 1.9699938763012859,
"grad_norm": 4.6972479820251465,
"learning_rate": 1.4514377930929235e-06,
"loss": 0.7591766834259033,
"step": 805,
"token_acc": 0.7624603242686797
},
{
"epoch": 1.9822412737293327,
"grad_norm": 4.843852996826172,
"learning_rate": 1.4209341762204587e-06,
"loss": 0.760959243774414,
"step": 810,
"token_acc": 0.7633743960301224
},
{
"epoch": 1.994488671157379,
"grad_norm": 4.634529113769531,
"learning_rate": 1.3906267278436359e-06,
"loss": 0.7314579963684082,
"step": 815,
"token_acc": 0.7712879191059074
},
{
"epoch": 2.0048989589712187,
"grad_norm": 4.321748733520508,
"learning_rate": 1.3605209576972843e-06,
"loss": 0.6995468139648438,
"step": 820,
"token_acc": 0.787699433865157
},
{
"epoch": 2.017146356399265,
"grad_norm": 4.254408836364746,
"learning_rate": 1.3306223388521939e-06,
"loss": 0.570511770248413,
"step": 825,
"token_acc": 0.8216209392358189
},
{
"epoch": 2.029393753827312,
"grad_norm": 4.720823287963867,
"learning_rate": 1.3009363067201371e-06,
"loss": 0.5582104206085206,
"step": 830,
"token_acc": 0.8252698576527759
},
{
"epoch": 2.0416411512553583,
"grad_norm": 4.739476203918457,
"learning_rate": 1.2714682580657379e-06,
"loss": 0.5444248199462891,
"step": 835,
"token_acc": 0.8246549425979275
},
{
"epoch": 2.0538885486834046,
"grad_norm": 5.198681831359863,
"learning_rate": 1.2422235500253687e-06,
"loss": 0.5460488319396972,
"step": 840,
"token_acc": 0.8272240085744909
},
{
"epoch": 2.0661359461114515,
"grad_norm": 5.516181468963623,
"learning_rate": 1.2132074991332542e-06,
"loss": 0.5592329978942872,
"step": 845,
"token_acc": 0.8220548006637068
},
{
"epoch": 2.078383343539498,
"grad_norm": 5.053701400756836,
"learning_rate": 1.18442538035495e-06,
"loss": 0.5448430061340332,
"step": 850,
"token_acc": 0.8223035387567496
},
{
"epoch": 2.090630740967544,
"grad_norm": 5.08636999130249,
"learning_rate": 1.1558824261283829e-06,
"loss": 0.5588015079498291,
"step": 855,
"token_acc": 0.8205888864290458
},
{
"epoch": 2.102878138395591,
"grad_norm": 5.013532638549805,
"learning_rate": 1.1275838254126214e-06,
"loss": 0.5484703063964844,
"step": 860,
"token_acc": 0.8259482905255996
},
{
"epoch": 2.1151255358236374,
"grad_norm": 4.854135990142822,
"learning_rate": 1.0995347227445502e-06,
"loss": 0.5305757045745849,
"step": 865,
"token_acc": 0.8284028801943264
},
{
"epoch": 2.127372933251684,
"grad_norm": 5.043030261993408,
"learning_rate": 1.0717402173036187e-06,
"loss": 0.5412274837493897,
"step": 870,
"token_acc": 0.8215913978494623
},
{
"epoch": 2.1396203306797306,
"grad_norm": 5.1244659423828125,
"learning_rate": 1.044205361984842e-06,
"loss": 0.5513949394226074,
"step": 875,
"token_acc": 0.8214534681073545
},
{
"epoch": 2.151867728107777,
"grad_norm": 5.117434501647949,
"learning_rate": 1.0169351624802035e-06,
"loss": 0.5630133152008057,
"step": 880,
"token_acc": 0.821359139413315
},
{
"epoch": 2.1641151255358237,
"grad_norm": 5.166259765625,
"learning_rate": 9.899345763686538e-07,
"loss": 0.5419129371643067,
"step": 885,
"token_acc": 0.8245680254990774
},
{
"epoch": 2.17636252296387,
"grad_norm": 5.291832447052002,
"learning_rate": 9.632085122148424e-07,
"loss": 0.5420055389404297,
"step": 890,
"token_acc": 0.8267434420985285
},
{
"epoch": 2.188609920391917,
"grad_norm": 5.194045543670654,
"learning_rate": 9.367618286767711e-07,
"loss": 0.521400260925293,
"step": 895,
"token_acc": 0.82656749906511
},
{
"epoch": 2.2008573178199633,
"grad_norm": 5.089542388916016,
"learning_rate": 9.105993336225161e-07,
"loss": 0.542095947265625,
"step": 900,
"token_acc": 0.8223984311719316
},
{
"epoch": 2.2131047152480097,
"grad_norm": 5.4029340744018555,
"learning_rate": 8.847257832561781e-07,
"loss": 0.5598678588867188,
"step": 905,
"token_acc": 0.8219299020040611
},
{
"epoch": 2.2253521126760565,
"grad_norm": 5.048251152038574,
"learning_rate": 8.591458812532336e-07,
"loss": 0.5180021286010742,
"step": 910,
"token_acc": 0.8336001348049541
},
{
"epoch": 2.237599510104103,
"grad_norm": 5.041197776794434,
"learning_rate": 8.338642779054288e-07,
"loss": 0.524175500869751,
"step": 915,
"token_acc": 0.8306564989562476
},
{
"epoch": 2.249846907532149,
"grad_norm": 5.465920925140381,
"learning_rate": 8.088855692753828e-07,
"loss": 0.5611342430114746,
"step": 920,
"token_acc": 0.8177949370420743
},
{
"epoch": 2.262094304960196,
"grad_norm": 5.163330078125,
"learning_rate": 7.842142963610467e-07,
"loss": 0.547283411026001,
"step": 925,
"token_acc": 0.8242695314132843
},
{
"epoch": 2.2743417023882424,
"grad_norm": 5.1077094078063965,
"learning_rate": 7.598549442701747e-07,
"loss": 0.5453132152557373,
"step": 930,
"token_acc": 0.822511007566366
},
{
"epoch": 2.286589099816289,
"grad_norm": 5.170557022094727,
"learning_rate": 7.358119414049542e-07,
"loss": 0.5626876831054688,
"step": 935,
"token_acc": 0.8234918200408998
},
{
"epoch": 2.2988364972443356,
"grad_norm": 4.865657329559326,
"learning_rate": 7.120896586569453e-07,
"loss": 0.5140172958374023,
"step": 940,
"token_acc": 0.8357797386730018
},
{
"epoch": 2.311083894672382,
"grad_norm": 5.453319072723389,
"learning_rate": 6.886924086124786e-07,
"loss": 0.5242246627807617,
"step": 945,
"token_acc": 0.8308014667365112
},
{
"epoch": 2.3233312921004288,
"grad_norm": 4.958571910858154,
"learning_rate": 6.656244447686458e-07,
"loss": 0.5323893547058105,
"step": 950,
"token_acc": 0.8292735877730016
},
{
"epoch": 2.335578689528475,
"grad_norm": 5.415950298309326,
"learning_rate": 6.428899607600364e-07,
"loss": 0.5338543891906739,
"step": 955,
"token_acc": 0.8275230158383874
},
{
"epoch": 2.3478260869565215,
"grad_norm": 5.205291748046875,
"learning_rate": 6.204930895963607e-07,
"loss": 0.5636034965515136,
"step": 960,
"token_acc": 0.8210286100663483
},
{
"epoch": 2.3600734843845683,
"grad_norm": 5.260465145111084,
"learning_rate": 5.984379029110888e-07,
"loss": 0.536073112487793,
"step": 965,
"token_acc": 0.8281601245028531
},
{
"epoch": 2.3723208818126147,
"grad_norm": 5.51268196105957,
"learning_rate": 5.767284102212464e-07,
"loss": 0.5502553462982178,
"step": 970,
"token_acc": 0.8222231730275543
},
{
"epoch": 2.3845682792406615,
"grad_norm": 5.176271438598633,
"learning_rate": 5.553685581985085e-07,
"loss": 0.5436900138854981,
"step": 975,
"token_acc": 0.8243608134334656
},
{
"epoch": 2.396815676668708,
"grad_norm": 5.452365398406982,
"learning_rate": 5.343622299517143e-07,
"loss": 0.5499383449554444,
"step": 980,
"token_acc": 0.821613554560618
},
{
"epoch": 2.4090630740967542,
"grad_norm": 5.364321231842041,
"learning_rate": 5.137132443209384e-07,
"loss": 0.5544261455535888,
"step": 985,
"token_acc": 0.8235047395352739
},
{
"epoch": 2.421310471524801,
"grad_norm": 5.1662492752075195,
"learning_rate": 4.934253551832463e-07,
"loss": 0.5553579330444336,
"step": 990,
"token_acc": 0.8218518036202631
},
{
"epoch": 2.4335578689528474,
"grad_norm": 5.128129959106445,
"learning_rate": 4.7350225077025805e-07,
"loss": 0.5611998558044433,
"step": 995,
"token_acc": 0.819782246026868
},
{
"epoch": 2.4458052663808942,
"grad_norm": 5.2355875968933105,
"learning_rate": 4.5394755299764867e-07,
"loss": 0.5385069847106934,
"step": 1000,
"token_acc": 0.8276789587852494
},
{
"epoch": 2.4580526638089406,
"grad_norm": 5.078090190887451,
"learning_rate": 4.3476481680670175e-07,
"loss": 0.5230921745300293,
"step": 1005,
"token_acc": 0.8339801638637344
},
{
"epoch": 2.470300061236987,
"grad_norm": 5.193488597869873,
"learning_rate": 4.159575295180396e-07,
"loss": 0.5407039642333984,
"step": 1010,
"token_acc": 0.8297552418344332
},
{
"epoch": 2.482547458665034,
"grad_norm": 5.043512344360352,
"learning_rate": 3.9752911019764946e-07,
"loss": 0.532266092300415,
"step": 1015,
"token_acc": 0.8278915329275042
},
{
"epoch": 2.49479485609308,
"grad_norm": 5.693848609924316,
"learning_rate": 3.7948290903531166e-07,
"loss": 0.560857105255127,
"step": 1020,
"token_acc": 0.8200070138523584
},
{
"epoch": 2.507042253521127,
"grad_norm": 5.108861446380615,
"learning_rate": 3.6182220673555256e-07,
"loss": 0.5424053192138671,
"step": 1025,
"token_acc": 0.8235603010677403
},
{
"epoch": 2.5192896509491733,
"grad_norm": 4.941168308258057,
"learning_rate": 3.445502139212334e-07,
"loss": 0.5431843757629394,
"step": 1030,
"token_acc": 0.8266571989474124
},
{
"epoch": 2.5315370483772197,
"grad_norm": 5.102714538574219,
"learning_rate": 3.276700705498745e-07,
"loss": 0.5414858818054199,
"step": 1035,
"token_acc": 0.82543195165546
},
{
"epoch": 2.5437844458052665,
"grad_norm": 5.438137531280518,
"learning_rate": 3.1118484534282484e-07,
"loss": 0.5353984832763672,
"step": 1040,
"token_acc": 0.8263861494630725
},
{
"epoch": 2.556031843233313,
"grad_norm": 5.2994771003723145,
"learning_rate": 2.95097535227388e-07,
"loss": 0.5479399681091308,
"step": 1045,
"token_acc": 0.8256810005139626
},
{
"epoch": 2.5682792406613597,
"grad_norm": 5.214596748352051,
"learning_rate": 2.7941106479199426e-07,
"loss": 0.516519832611084,
"step": 1050,
"token_acc": 0.8335078095557138
},
{
"epoch": 2.580526638089406,
"grad_norm": 5.224749565124512,
"learning_rate": 2.641282857545274e-07,
"loss": 0.5579429626464844,
"step": 1055,
"token_acc": 0.82092176315459
},
{
"epoch": 2.5927740355174524,
"grad_norm": 5.229243278503418,
"learning_rate": 2.492519764438966e-07,
"loss": 0.5679381370544434,
"step": 1060,
"token_acc": 0.8221638384012404
},
{
"epoch": 2.605021432945499,
"grad_norm": 5.2897796630859375,
"learning_rate": 2.3478484129495077e-07,
"loss": 0.5454854011535645,
"step": 1065,
"token_acc": 0.825406647807638
},
{
"epoch": 2.6172688303735456,
"grad_norm": 5.087146282196045,
"learning_rate": 2.2072951035682688e-07,
"loss": 0.5423697471618653,
"step": 1070,
"token_acc": 0.8259176156809619
},
{
"epoch": 2.629516227801592,
"grad_norm": 5.195399284362793,
"learning_rate": 2.0708853881481973e-07,
"loss": 0.5481161117553711,
"step": 1075,
"token_acc": 0.8264214919144497
},
{
"epoch": 2.641763625229639,
"grad_norm": 5.070648193359375,
"learning_rate": 1.9386440652586546e-07,
"loss": 0.5489974021911621,
"step": 1080,
"token_acc": 0.8267874695499807
},
{
"epoch": 2.654011022657685,
"grad_norm": 5.130269527435303,
"learning_rate": 1.8105951756771322e-07,
"loss": 0.538370418548584,
"step": 1085,
"token_acc": 0.8281619830442828
},
{
"epoch": 2.6662584200857316,
"grad_norm": 5.335844039916992,
"learning_rate": 1.686761998018785e-07,
"loss": 0.5541041374206543,
"step": 1090,
"token_acc": 0.8237131544214694
},
{
"epoch": 2.6785058175137784,
"grad_norm": 5.29373836517334,
"learning_rate": 1.5671670445044918e-07,
"loss": 0.5493666648864746,
"step": 1095,
"token_acc": 0.8230841200986646
},
{
"epoch": 2.6907532149418247,
"grad_norm": 5.108797550201416,
"learning_rate": 1.4518320568682602e-07,
"loss": 0.5377497673034668,
"step": 1100,
"token_acc": 0.831723794918556
},
{
"epoch": 2.7030006123698715,
"grad_norm": 5.346076488494873,
"learning_rate": 1.340778002404694e-07,
"loss": 0.5413017272949219,
"step": 1105,
"token_acc": 0.8275166608207647
},
{
"epoch": 2.715248009797918,
"grad_norm": 5.399250030517578,
"learning_rate": 1.234025070157238e-07,
"loss": 0.5543554306030274,
"step": 1110,
"token_acc": 0.8235164641662265
},
{
"epoch": 2.7274954072259643,
"grad_norm": 5.150039196014404,
"learning_rate": 1.1315926672479243e-07,
"loss": 0.5648593902587891,
"step": 1115,
"token_acc": 0.8208603931482369
},
{
"epoch": 2.739742804654011,
"grad_norm": 5.281070709228516,
"learning_rate": 1.033499415349265e-07,
"loss": 0.5491425514221191,
"step": 1120,
"token_acc": 0.8220901479328445
},
{
"epoch": 2.7519902020820575,
"grad_norm": 5.146131992340088,
"learning_rate": 9.397631472989138e-08,
"loss": 0.5133252143859863,
"step": 1125,
"token_acc": 0.8336260441207968
},
{
"epoch": 2.7642375995101043,
"grad_norm": 5.330942630767822,
"learning_rate": 8.504009038577621e-08,
"loss": 0.5365485191345215,
"step": 1130,
"token_acc": 0.8278971095200213
},
{
"epoch": 2.7764849969381507,
"grad_norm": 5.198803424835205,
"learning_rate": 7.654289306120194e-08,
"loss": 0.5431034088134765,
"step": 1135,
"token_acc": 0.8274643334339037
},
{
"epoch": 2.788732394366197,
"grad_norm": 5.1973557472229,
"learning_rate": 6.848626750198428e-08,
"loss": 0.5288222312927247,
"step": 1140,
"token_acc": 0.8275166344709165
},
{
"epoch": 2.800979791794244,
"grad_norm": 5.35372257232666,
"learning_rate": 6.08716783603075e-08,
"loss": 0.5239756107330322,
"step": 1145,
"token_acc": 0.8283219340129909
},
{
"epoch": 2.81322718922229,
"grad_norm": 5.1523661613464355,
"learning_rate": 5.3700509928458765e-08,
"loss": 0.5328633308410644,
"step": 1150,
"token_acc": 0.8294553262346085
},
{
"epoch": 2.825474586650337,
"grad_norm": 5.435372352600098,
"learning_rate": 4.697406588717007e-08,
"loss": 0.5283485412597656,
"step": 1155,
"token_acc": 0.828381102638268
},
{
"epoch": 2.8377219840783834,
"grad_norm": 5.170069217681885,
"learning_rate": 4.069356906861721e-08,
"loss": 0.5555888175964355,
"step": 1160,
"token_acc": 0.82186616399623
},
{
"epoch": 2.8499693815064298,
"grad_norm": 5.208567142486572,
"learning_rate": 3.486016123411345e-08,
"loss": 0.5386466026306153,
"step": 1165,
"token_acc": 0.8267478554602427
},
{
"epoch": 2.8622167789344766,
"grad_norm": 5.432430744171143,
"learning_rate": 2.947490286654503e-08,
"loss": 0.5284968852996826,
"step": 1170,
"token_acc": 0.8326574172892209
},
{
"epoch": 2.874464176362523,
"grad_norm": 5.190342426300049,
"learning_rate": 2.453877297758117e-08,
"loss": 0.5291720867156983,
"step": 1175,
"token_acc": 0.8325078206465067
},
{
"epoch": 2.8867115737905698,
"grad_norm": 5.376348495483398,
"learning_rate": 2.0052668929692875e-08,
"loss": 0.5356964111328125,
"step": 1180,
"token_acc": 0.8268531588177425
},
{
"epoch": 2.898958971218616,
"grad_norm": 5.295315265655518,
"learning_rate": 1.601740627301951e-08,
"loss": 0.5229966163635253,
"step": 1185,
"token_acc": 0.8315890878836975
},
{
"epoch": 2.9112063686466625,
"grad_norm": 5.423808574676514,
"learning_rate": 1.2433718597103795e-08,
"loss": 0.5427167415618896,
"step": 1190,
"token_acc": 0.8261059817091848
},
{
"epoch": 2.923453766074709,
"grad_norm": 5.136529445648193,
"learning_rate": 9.302257397531267e-09,
"loss": 0.550775671005249,
"step": 1195,
"token_acc": 0.8222147396775958
},
{
"epoch": 2.9357011635027557,
"grad_norm": 5.073871612548828,
"learning_rate": 6.623591957490016e-09,
"loss": 0.5416533470153808,
"step": 1200,
"token_acc": 0.8258615561126929
},
{
"epoch": 2.947948560930802,
"grad_norm": 5.151060104370117,
"learning_rate": 4.398209244279305e-09,
"loss": 0.554953670501709,
"step": 1205,
"token_acc": 0.8215449660882586
},
{
"epoch": 2.960195958358849,
"grad_norm": 5.362220287322998,
"learning_rate": 2.6265138207806628e-09,
"loss": 0.5322298526763916,
"step": 1210,
"token_acc": 0.8296142535893444
},
{
"epoch": 2.9724433557868952,
"grad_norm": 5.357572555541992,
"learning_rate": 1.308827771910881e-09,
"loss": 0.5438649177551269,
"step": 1215,
"token_acc": 0.8253160112359551
},
{
"epoch": 2.9846907532149416,
"grad_norm": 5.009280204772949,
"learning_rate": 4.4539064606829996e-10,
"loss": 0.5299254417419433,
"step": 1220,
"token_acc": 0.826584919317069
},
{
"epoch": 2.9969381506429884,
"grad_norm": 5.41025972366333,
"learning_rate": 3.6359411584308e-11,
"loss": 0.5463360786437989,
"step": 1225,
"token_acc": 0.8289374529012811
}
],
"logging_steps": 5,
"max_steps": 1227,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 6.549139944563016e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}