MiniNeko-1B / trainer_state.json
liumindmind's picture
Upload folder using huggingface_hub
56018c2 verified
Raw
History Blame Contribute Delete
109 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 500,
"global_step": 4820,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0010378827192527244,
"grad_norm": 17.360599517822266,
"learning_rate": 1.3793103448275863e-07,
"loss": 3.990642547607422,
"step": 1,
"token_acc": 0.3084232295567604
},
{
"epoch": 0.010378827192527244,
"grad_norm": 13.039176940917969,
"learning_rate": 1.3793103448275862e-06,
"loss": 3.8488650851779513,
"step": 10,
"token_acc": 0.3284105060568323
},
{
"epoch": 0.02075765438505449,
"grad_norm": 5.6738457679748535,
"learning_rate": 2.7586206896551725e-06,
"loss": 3.7818458557128904,
"step": 20,
"token_acc": 0.32973962055664535
},
{
"epoch": 0.031136481577581733,
"grad_norm": 3.4473679065704346,
"learning_rate": 4.137931034482759e-06,
"loss": 3.5191299438476564,
"step": 30,
"token_acc": 0.357729861270408
},
{
"epoch": 0.04151530877010898,
"grad_norm": 2.84421443939209,
"learning_rate": 5.517241379310345e-06,
"loss": 3.3019275665283203,
"step": 40,
"token_acc": 0.3810691861990996
},
{
"epoch": 0.05189413596263622,
"grad_norm": 2.5887951850891113,
"learning_rate": 6.896551724137932e-06,
"loss": 3.20899658203125,
"step": 50,
"token_acc": 0.3901559578990499
},
{
"epoch": 0.062272963155163466,
"grad_norm": 2.701371431350708,
"learning_rate": 8.275862068965518e-06,
"loss": 3.107984924316406,
"step": 60,
"token_acc": 0.4010707935593456
},
{
"epoch": 0.07265179034769072,
"grad_norm": 2.5003151893615723,
"learning_rate": 9.655172413793105e-06,
"loss": 2.9776824951171874,
"step": 70,
"token_acc": 0.4182194194091965
},
{
"epoch": 0.08303061754021795,
"grad_norm": 3.191375255584717,
"learning_rate": 1.103448275862069e-05,
"loss": 2.9078922271728516,
"step": 80,
"token_acc": 0.42640041076030927
},
{
"epoch": 0.0934094447327452,
"grad_norm": 3.1060311794281006,
"learning_rate": 1.2413793103448277e-05,
"loss": 2.8590766906738283,
"step": 90,
"token_acc": 0.4328527750116345
},
{
"epoch": 0.10378827192527244,
"grad_norm": 2.9473307132720947,
"learning_rate": 1.3793103448275863e-05,
"loss": 2.8455408096313475,
"step": 100,
"token_acc": 0.431822659077006
},
{
"epoch": 0.1141670991177997,
"grad_norm": 2.989382028579712,
"learning_rate": 1.5172413793103448e-05,
"loss": 2.806658172607422,
"step": 110,
"token_acc": 0.43548568507157465
},
{
"epoch": 0.12454592631032693,
"grad_norm": 2.520890712738037,
"learning_rate": 1.6551724137931037e-05,
"loss": 2.710813522338867,
"step": 120,
"token_acc": 0.44830804780956895
},
{
"epoch": 0.13492475350285418,
"grad_norm": 2.522371530532837,
"learning_rate": 1.7931034482758623e-05,
"loss": 2.7086956024169924,
"step": 130,
"token_acc": 0.4483404605908431
},
{
"epoch": 0.14530358069538143,
"grad_norm": 2.554992914199829,
"learning_rate": 1.931034482758621e-05,
"loss": 2.7071361541748047,
"step": 140,
"token_acc": 0.44866705920571753
},
{
"epoch": 0.15568240788790866,
"grad_norm": 2.8297841548919678,
"learning_rate": 1.9999943552317106e-05,
"loss": 2.7326435089111327,
"step": 150,
"token_acc": 0.4446824376854364
},
{
"epoch": 0.1660612350804359,
"grad_norm": 2.8616182804107666,
"learning_rate": 1.999949197467755e-05,
"loss": 2.6460166931152345,
"step": 160,
"token_acc": 0.45594791592951667
},
{
"epoch": 0.17644006227296316,
"grad_norm": 2.4682888984680176,
"learning_rate": 1.9998588839790777e-05,
"loss": 2.686064910888672,
"step": 170,
"token_acc": 0.4503634107427761
},
{
"epoch": 0.1868188894654904,
"grad_norm": 2.6717631816864014,
"learning_rate": 1.9997234188440587e-05,
"loss": 2.680805206298828,
"step": 180,
"token_acc": 0.45006424662513245
},
{
"epoch": 0.19719771665801764,
"grad_norm": 2.4356844425201416,
"learning_rate": 1.9995428081800335e-05,
"loss": 2.643203926086426,
"step": 190,
"token_acc": 0.4544208223707422
},
{
"epoch": 0.2075765438505449,
"grad_norm": 2.5181164741516113,
"learning_rate": 1.9993170601430233e-05,
"loss": 2.6210107803344727,
"step": 200,
"token_acc": 0.4591047422659873
},
{
"epoch": 0.21795537104307214,
"grad_norm": 2.349583387374878,
"learning_rate": 1.999046184927361e-05,
"loss": 2.6063869476318358,
"step": 210,
"token_acc": 0.46119800400418715
},
{
"epoch": 0.2283341982355994,
"grad_norm": 2.4258267879486084,
"learning_rate": 1.9987301947652354e-05,
"loss": 2.5811992645263673,
"step": 220,
"token_acc": 0.462792299200956
},
{
"epoch": 0.2387130254281266,
"grad_norm": 2.268512487411499,
"learning_rate": 1.9983691039261358e-05,
"loss": 2.603193664550781,
"step": 230,
"token_acc": 0.4602403687849852
},
{
"epoch": 0.24909185262065386,
"grad_norm": 2.190422773361206,
"learning_rate": 1.9979629287162096e-05,
"loss": 2.559502601623535,
"step": 240,
"token_acc": 0.4673703308324187
},
{
"epoch": 0.2594706798131811,
"grad_norm": 2.487339735031128,
"learning_rate": 1.9975116874775243e-05,
"loss": 2.545312690734863,
"step": 250,
"token_acc": 0.468937618225183
},
{
"epoch": 0.26984950700570837,
"grad_norm": 2.2605233192443848,
"learning_rate": 1.9970154005872403e-05,
"loss": 2.5477973937988283,
"step": 260,
"token_acc": 0.46680020435312625
},
{
"epoch": 0.2802283341982356,
"grad_norm": 2.355224847793579,
"learning_rate": 1.9964740904566903e-05,
"loss": 2.54384708404541,
"step": 270,
"token_acc": 0.46990711025073556
},
{
"epoch": 0.29060716139076287,
"grad_norm": 2.4003963470458984,
"learning_rate": 1.9958877815303672e-05,
"loss": 2.489452362060547,
"step": 280,
"token_acc": 0.47418303210494744
},
{
"epoch": 0.30098598858329007,
"grad_norm": 2.130462646484375,
"learning_rate": 1.9952565002848213e-05,
"loss": 2.497241973876953,
"step": 290,
"token_acc": 0.47516422139439124
},
{
"epoch": 0.3113648157758173,
"grad_norm": 2.237414836883545,
"learning_rate": 1.994580275227462e-05,
"loss": 2.525006103515625,
"step": 300,
"token_acc": 0.4737206296872933
},
{
"epoch": 0.32174364296834457,
"grad_norm": 2.4160428047180176,
"learning_rate": 1.993859136895274e-05,
"loss": 2.5184478759765625,
"step": 310,
"token_acc": 0.4719125116300352
},
{
"epoch": 0.3321224701608718,
"grad_norm": 2.338179588317871,
"learning_rate": 1.9930931178534353e-05,
"loss": 2.512801742553711,
"step": 320,
"token_acc": 0.4706307636304805
},
{
"epoch": 0.34250129735339907,
"grad_norm": 2.302748680114746,
"learning_rate": 1.992282252693848e-05,
"loss": 2.4969722747802736,
"step": 330,
"token_acc": 0.4733330627403627
},
{
"epoch": 0.3528801245459263,
"grad_norm": 2.033113479614258,
"learning_rate": 1.9914265780335768e-05,
"loss": 2.522578811645508,
"step": 340,
"token_acc": 0.4707610297704945
},
{
"epoch": 0.3632589517384536,
"grad_norm": 2.232757091522217,
"learning_rate": 1.990526132513194e-05,
"loss": 2.4406387329101564,
"step": 350,
"token_acc": 0.48246498599439774
},
{
"epoch": 0.3736377789309808,
"grad_norm": 2.2933907508850098,
"learning_rate": 1.9895809567950355e-05,
"loss": 2.4779022216796873,
"step": 360,
"token_acc": 0.4767427240860788
},
{
"epoch": 0.384016606123508,
"grad_norm": 2.354503870010376,
"learning_rate": 1.988591093561364e-05,
"loss": 2.4425716400146484,
"step": 370,
"token_acc": 0.4801819564981137
},
{
"epoch": 0.39439543331603527,
"grad_norm": 2.303921699523926,
"learning_rate": 1.987556587512442e-05,
"loss": 2.424735260009766,
"step": 380,
"token_acc": 0.48574599146146613
},
{
"epoch": 0.4047742605085625,
"grad_norm": 2.117462158203125,
"learning_rate": 1.9864774853645136e-05,
"loss": 2.390948486328125,
"step": 390,
"token_acc": 0.4894718362842955
},
{
"epoch": 0.4151530877010898,
"grad_norm": 2.1252524852752686,
"learning_rate": 1.9853538358476933e-05,
"loss": 2.4562961578369142,
"step": 400,
"token_acc": 0.47807169217270123
},
{
"epoch": 0.425531914893617,
"grad_norm": 2.2925615310668945,
"learning_rate": 1.9841856897037673e-05,
"loss": 2.4759357452392576,
"step": 410,
"token_acc": 0.4745784350231395
},
{
"epoch": 0.4359107420861443,
"grad_norm": 2.256213426589966,
"learning_rate": 1.982973099683902e-05,
"loss": 2.41542911529541,
"step": 420,
"token_acc": 0.48397429241854767
},
{
"epoch": 0.4462895692786715,
"grad_norm": 2.2051868438720703,
"learning_rate": 1.9817161205462594e-05,
"loss": 2.391830253601074,
"step": 430,
"token_acc": 0.48866532118321
},
{
"epoch": 0.4566683964711988,
"grad_norm": 2.1445558071136475,
"learning_rate": 1.980414809053528e-05,
"loss": 2.4202728271484375,
"step": 440,
"token_acc": 0.48447691624371814
},
{
"epoch": 0.467047223663726,
"grad_norm": 1.9786752462387085,
"learning_rate": 1.9790692239703556e-05,
"loss": 2.429086685180664,
"step": 450,
"token_acc": 0.48086049207780496
},
{
"epoch": 0.4774260508562532,
"grad_norm": 2.115772008895874,
"learning_rate": 1.9776794260607e-05,
"loss": 2.4210033416748047,
"step": 460,
"token_acc": 0.48356514424475844
},
{
"epoch": 0.4878048780487805,
"grad_norm": 2.1354856491088867,
"learning_rate": 1.9762454780850807e-05,
"loss": 2.4250818252563477,
"step": 470,
"token_acc": 0.4829121066582684
},
{
"epoch": 0.49818370524130773,
"grad_norm": 2.2114412784576416,
"learning_rate": 1.9747674447977473e-05,
"loss": 2.414927101135254,
"step": 480,
"token_acc": 0.482086258776329
},
{
"epoch": 0.508562532433835,
"grad_norm": 2.1250457763671875,
"learning_rate": 1.9732453929437553e-05,
"loss": 2.3822227478027345,
"step": 490,
"token_acc": 0.48768738756745955
},
{
"epoch": 0.5189413596263622,
"grad_norm": 2.1776046752929688,
"learning_rate": 1.971679391255951e-05,
"loss": 2.3865856170654296,
"step": 500,
"token_acc": 0.4889711492549803
},
{
"epoch": 0.5293201868188895,
"grad_norm": 2.0361459255218506,
"learning_rate": 1.9700695104518677e-05,
"loss": 2.4085275650024416,
"step": 510,
"token_acc": 0.4852330351909895
},
{
"epoch": 0.5396990140114167,
"grad_norm": 2.078922748565674,
"learning_rate": 1.968415823230534e-05,
"loss": 2.3532440185546877,
"step": 520,
"token_acc": 0.49322279919859346
},
{
"epoch": 0.550077841203944,
"grad_norm": 2.177894115447998,
"learning_rate": 1.9667184042691877e-05,
"loss": 2.375431442260742,
"step": 530,
"token_acc": 0.4892896268660484
},
{
"epoch": 0.5604566683964712,
"grad_norm": 2.0301597118377686,
"learning_rate": 1.9649773302199067e-05,
"loss": 2.420338439941406,
"step": 540,
"token_acc": 0.48254752179718796
},
{
"epoch": 0.5708354955889985,
"grad_norm": 2.0769824981689453,
"learning_rate": 1.9631926797061455e-05,
"loss": 2.3777694702148438,
"step": 550,
"token_acc": 0.49080419926710905
},
{
"epoch": 0.5812143227815257,
"grad_norm": 2.0202431678771973,
"learning_rate": 1.9613645333191863e-05,
"loss": 2.424168014526367,
"step": 560,
"token_acc": 0.4841990720449771
},
{
"epoch": 0.5915931499740529,
"grad_norm": 1.9847513437271118,
"learning_rate": 1.9594929736144978e-05,
"loss": 2.3798294067382812,
"step": 570,
"token_acc": 0.487947249514002
},
{
"epoch": 0.6019719771665801,
"grad_norm": 1.8895344734191895,
"learning_rate": 1.9575780851080076e-05,
"loss": 2.3693519592285157,
"step": 580,
"token_acc": 0.4903529816676283
},
{
"epoch": 0.6123508043591074,
"grad_norm": 1.8537346124649048,
"learning_rate": 1.9556199542722884e-05,
"loss": 2.351144790649414,
"step": 590,
"token_acc": 0.49225624225624226
},
{
"epoch": 0.6227296315516346,
"grad_norm": 1.975832462310791,
"learning_rate": 1.9536186695326486e-05,
"loss": 2.4092937469482423,
"step": 600,
"token_acc": 0.4848559870470041
},
{
"epoch": 0.6331084587441619,
"grad_norm": 2.202850818634033,
"learning_rate": 1.9515743212631424e-05,
"loss": 2.3731868743896483,
"step": 610,
"token_acc": 0.4905812919395262
},
{
"epoch": 0.6434872859366891,
"grad_norm": 2.2077083587646484,
"learning_rate": 1.9494870017824877e-05,
"loss": 2.358300971984863,
"step": 620,
"token_acc": 0.49231482881014055
},
{
"epoch": 0.6538661131292164,
"grad_norm": 1.9416003227233887,
"learning_rate": 1.9473568053498962e-05,
"loss": 2.3593875885009767,
"step": 630,
"token_acc": 0.48989922301715516
},
{
"epoch": 0.6642449403217436,
"grad_norm": 2.105966567993164,
"learning_rate": 1.94518382816082e-05,
"loss": 2.3033672332763673,
"step": 640,
"token_acc": 0.4987161991407632
},
{
"epoch": 0.6746237675142709,
"grad_norm": 2.1623332500457764,
"learning_rate": 1.9429681683426022e-05,
"loss": 2.3448612213134767,
"step": 650,
"token_acc": 0.49277714656711574
},
{
"epoch": 0.6850025947067981,
"grad_norm": 2.0965728759765625,
"learning_rate": 1.9407099259500524e-05,
"loss": 2.3009931564331056,
"step": 660,
"token_acc": 0.49894616918256907
},
{
"epoch": 0.6953814218993254,
"grad_norm": 1.925125002861023,
"learning_rate": 1.938409202960922e-05,
"loss": 2.3482454299926756,
"step": 670,
"token_acc": 0.4938581741660709
},
{
"epoch": 0.7057602490918526,
"grad_norm": 2.002753496170044,
"learning_rate": 1.9360661032713035e-05,
"loss": 2.2995315551757813,
"step": 680,
"token_acc": 0.49933824627538226
},
{
"epoch": 0.7161390762843799,
"grad_norm": 2.0246741771698,
"learning_rate": 1.933680732690937e-05,
"loss": 2.349001884460449,
"step": 690,
"token_acc": 0.49122770996519827
},
{
"epoch": 0.7265179034769071,
"grad_norm": 2.026449203491211,
"learning_rate": 1.931253198938432e-05,
"loss": 2.3147819519042967,
"step": 700,
"token_acc": 0.49539013488866174
},
{
"epoch": 0.7368967306694344,
"grad_norm": 1.8472758531570435,
"learning_rate": 1.9287836116364035e-05,
"loss": 2.3027347564697265,
"step": 710,
"token_acc": 0.4981742332820107
},
{
"epoch": 0.7472755578619616,
"grad_norm": 1.8673181533813477,
"learning_rate": 1.9262720823065217e-05,
"loss": 2.317824935913086,
"step": 720,
"token_acc": 0.4963641915566436
},
{
"epoch": 0.7576543850544888,
"grad_norm": 2.106228828430176,
"learning_rate": 1.9237187243644752e-05,
"loss": 2.3398685455322266,
"step": 730,
"token_acc": 0.4956010253362811
},
{
"epoch": 0.768033212247016,
"grad_norm": 1.951507568359375,
"learning_rate": 1.92112365311485e-05,
"loss": 2.304329681396484,
"step": 740,
"token_acc": 0.4985643448423325
},
{
"epoch": 0.7784120394395433,
"grad_norm": 1.9027397632598877,
"learning_rate": 1.9184869857459233e-05,
"loss": 2.2993040084838867,
"step": 750,
"token_acc": 0.49950871574657013
},
{
"epoch": 0.7887908666320705,
"grad_norm": 2.003692865371704,
"learning_rate": 1.9158088413243688e-05,
"loss": 2.3015514373779298,
"step": 760,
"token_acc": 0.4992930038116316
},
{
"epoch": 0.7991696938245978,
"grad_norm": 1.894520878791809,
"learning_rate": 1.9130893407898834e-05,
"loss": 2.3123340606689453,
"step": 770,
"token_acc": 0.49717116013071894
},
{
"epoch": 0.809548521017125,
"grad_norm": 1.9188441038131714,
"learning_rate": 1.9103286069497233e-05,
"loss": 2.319204902648926,
"step": 780,
"token_acc": 0.49715919063260033
},
{
"epoch": 0.8199273482096523,
"grad_norm": 1.950253963470459,
"learning_rate": 1.9075267644731596e-05,
"loss": 2.281215286254883,
"step": 790,
"token_acc": 0.5036784967120927
},
{
"epoch": 0.8303061754021795,
"grad_norm": 1.762008786201477,
"learning_rate": 1.9046839398858476e-05,
"loss": 2.3167495727539062,
"step": 800,
"token_acc": 0.4997348792816996
},
{
"epoch": 0.8406850025947068,
"grad_norm": 2.015512704849243,
"learning_rate": 1.9018002615641136e-05,
"loss": 2.3037847518920898,
"step": 810,
"token_acc": 0.4994212962962963
},
{
"epoch": 0.851063829787234,
"grad_norm": 1.8968827724456787,
"learning_rate": 1.8988758597291577e-05,
"loss": 2.310440254211426,
"step": 820,
"token_acc": 0.4973895748736223
},
{
"epoch": 0.8614426569797613,
"grad_norm": 1.8723076581954956,
"learning_rate": 1.895910866441173e-05,
"loss": 2.3250904083251953,
"step": 830,
"token_acc": 0.49634746185098855
},
{
"epoch": 0.8718214841722886,
"grad_norm": 2.014148473739624,
"learning_rate": 1.8929054155933825e-05,
"loss": 2.3208742141723633,
"step": 840,
"token_acc": 0.4968101202639255
},
{
"epoch": 0.8822003113648158,
"grad_norm": 2.0068304538726807,
"learning_rate": 1.889859642905992e-05,
"loss": 2.3008609771728517,
"step": 850,
"token_acc": 0.498759382494316
},
{
"epoch": 0.892579138557343,
"grad_norm": 1.8189960718154907,
"learning_rate": 1.886773685920062e-05,
"loss": 2.2901611328125,
"step": 860,
"token_acc": 0.49776350075429104
},
{
"epoch": 0.9029579657498703,
"grad_norm": 1.8811589479446411,
"learning_rate": 1.8836476839912967e-05,
"loss": 2.2908302307128907,
"step": 870,
"token_acc": 0.5012921115671505
},
{
"epoch": 0.9133367929423976,
"grad_norm": 1.9208338260650635,
"learning_rate": 1.88048177828375e-05,
"loss": 2.300111198425293,
"step": 880,
"token_acc": 0.4994018028424679
},
{
"epoch": 0.9237156201349248,
"grad_norm": 2.0872278213500977,
"learning_rate": 1.8772761117634514e-05,
"loss": 2.2796253204345702,
"step": 890,
"token_acc": 0.5026472365308401
},
{
"epoch": 0.934094447327452,
"grad_norm": 1.9212771654129028,
"learning_rate": 1.8740308291919496e-05,
"loss": 2.312908935546875,
"step": 900,
"token_acc": 0.4986565203878044
},
{
"epoch": 0.9444732745199792,
"grad_norm": 1.977607250213623,
"learning_rate": 1.8707460771197773e-05,
"loss": 2.2796945571899414,
"step": 910,
"token_acc": 0.501866042106871
},
{
"epoch": 0.9548521017125065,
"grad_norm": 1.734717845916748,
"learning_rate": 1.86742200387983e-05,
"loss": 2.27264518737793,
"step": 920,
"token_acc": 0.50150849683934
},
{
"epoch": 0.9652309289050337,
"grad_norm": 1.970118522644043,
"learning_rate": 1.8640587595806695e-05,
"loss": 2.2312889099121094,
"step": 930,
"token_acc": 0.508051521310992
},
{
"epoch": 0.975609756097561,
"grad_norm": 1.846427083015442,
"learning_rate": 1.8606564960997456e-05,
"loss": 2.3052406311035156,
"step": 940,
"token_acc": 0.4963708614642256
},
{
"epoch": 0.9859885832900882,
"grad_norm": 1.8627911806106567,
"learning_rate": 1.8572153670765363e-05,
"loss": 2.2622812271118162,
"step": 950,
"token_acc": 0.5032906868627054
},
{
"epoch": 0.9963674104826155,
"grad_norm": 1.8354142904281616,
"learning_rate": 1.8537355279056116e-05,
"loss": 2.280261993408203,
"step": 960,
"token_acc": 0.5012286671688703
},
{
"epoch": 1.0062272963155163,
"grad_norm": 1.8173019886016846,
"learning_rate": 1.8502171357296144e-05,
"loss": 2.2140834808349608,
"step": 970,
"token_acc": 0.5118705821565734
},
{
"epoch": 1.0166061235080437,
"grad_norm": 1.7486186027526855,
"learning_rate": 1.8466603494321644e-05,
"loss": 2.152490997314453,
"step": 980,
"token_acc": 0.5221414477643967
},
{
"epoch": 1.0269849507005708,
"grad_norm": 1.873517394065857,
"learning_rate": 1.8430653296306844e-05,
"loss": 2.113158416748047,
"step": 990,
"token_acc": 0.5261487203709629
},
{
"epoch": 1.037363777893098,
"grad_norm": 1.8462716341018677,
"learning_rate": 1.839432238669147e-05,
"loss": 2.143682670593262,
"step": 1000,
"token_acc": 0.5217496898181146
},
{
"epoch": 1.0477426050856253,
"grad_norm": 1.992281436920166,
"learning_rate": 1.8357612406107417e-05,
"loss": 2.131803512573242,
"step": 1010,
"token_acc": 0.5236756053031728
},
{
"epoch": 1.0581214322781525,
"grad_norm": 1.843721866607666,
"learning_rate": 1.8320525012304685e-05,
"loss": 2.178090286254883,
"step": 1020,
"token_acc": 0.5173009689341724
},
{
"epoch": 1.0685002594706798,
"grad_norm": 1.9136370420455933,
"learning_rate": 1.82830618800765e-05,
"loss": 2.1309703826904296,
"step": 1030,
"token_acc": 0.5241540126294827
},
{
"epoch": 1.078879086663207,
"grad_norm": 1.8477224111557007,
"learning_rate": 1.8245224701183694e-05,
"loss": 2.118892288208008,
"step": 1040,
"token_acc": 0.5239186024464362
},
{
"epoch": 1.0892579138557343,
"grad_norm": 1.8208996057510376,
"learning_rate": 1.8207015184278307e-05,
"loss": 2.134159278869629,
"step": 1050,
"token_acc": 0.5229746350148978
},
{
"epoch": 1.0996367410482615,
"grad_norm": 1.8434394598007202,
"learning_rate": 1.8168435054826426e-05,
"loss": 2.148929786682129,
"step": 1060,
"token_acc": 0.5197092810025363
},
{
"epoch": 1.1100155682407888,
"grad_norm": 2.0058698654174805,
"learning_rate": 1.8129486055030255e-05,
"loss": 2.1446609497070312,
"step": 1070,
"token_acc": 0.5195033658050477
},
{
"epoch": 1.120394395433316,
"grad_norm": 1.959863305091858,
"learning_rate": 1.8090169943749477e-05,
"loss": 2.143418312072754,
"step": 1080,
"token_acc": 0.5213631533674037
},
{
"epoch": 1.1307732226258433,
"grad_norm": 1.7750418186187744,
"learning_rate": 1.8050488496421775e-05,
"loss": 2.1282272338867188,
"step": 1090,
"token_acc": 0.5217282155614713
},
{
"epoch": 1.1411520498183705,
"grad_norm": 1.8564324378967285,
"learning_rate": 1.8010443504982697e-05,
"loss": 2.1531448364257812,
"step": 1100,
"token_acc": 0.5194386957807154
},
{
"epoch": 1.1515308770108978,
"grad_norm": 1.8262008428573608,
"learning_rate": 1.797003677778472e-05,
"loss": 2.1420780181884767,
"step": 1110,
"token_acc": 0.5192408819930753
},
{
"epoch": 1.161909704203425,
"grad_norm": 1.8797789812088013,
"learning_rate": 1.7929270139515606e-05,
"loss": 2.1487682342529295,
"step": 1120,
"token_acc": 0.5204034356178053
},
{
"epoch": 1.1722885313959523,
"grad_norm": 1.8128505945205688,
"learning_rate": 1.788814543111596e-05,
"loss": 2.104275131225586,
"step": 1130,
"token_acc": 0.5252394842123719
},
{
"epoch": 1.1826673585884795,
"grad_norm": 1.7701231241226196,
"learning_rate": 1.7846664509696145e-05,
"loss": 2.1125534057617186,
"step": 1140,
"token_acc": 0.5259930362748606
},
{
"epoch": 1.1930461857810069,
"grad_norm": 1.974525809288025,
"learning_rate": 1.7804829248452394e-05,
"loss": 2.1423641204833985,
"step": 1150,
"token_acc": 0.5217040115741096
},
{
"epoch": 1.203425012973534,
"grad_norm": 1.8292217254638672,
"learning_rate": 1.7762641536582227e-05,
"loss": 2.119368553161621,
"step": 1160,
"token_acc": 0.5242369655186491
},
{
"epoch": 1.2138038401660611,
"grad_norm": 1.8477205038070679,
"learning_rate": 1.772010327919912e-05,
"loss": 2.1484371185302735,
"step": 1170,
"token_acc": 0.5193583042373406
},
{
"epoch": 1.2241826673585885,
"grad_norm": 1.9517289400100708,
"learning_rate": 1.7677216397246514e-05,
"loss": 2.134074401855469,
"step": 1180,
"token_acc": 0.5212832534805224
},
{
"epoch": 1.2345614945511156,
"grad_norm": 1.8498804569244385,
"learning_rate": 1.763398282741103e-05,
"loss": 2.107711601257324,
"step": 1190,
"token_acc": 0.5256155964811313
},
{
"epoch": 1.244940321743643,
"grad_norm": 1.7352577447891235,
"learning_rate": 1.759040452203503e-05,
"loss": 2.1284027099609375,
"step": 1200,
"token_acc": 0.5242071524966262
},
{
"epoch": 1.2553191489361701,
"grad_norm": 1.918878436088562,
"learning_rate": 1.754648344902845e-05,
"loss": 2.122066879272461,
"step": 1210,
"token_acc": 0.5263007629830174
},
{
"epoch": 1.2656979761286975,
"grad_norm": 1.7493046522140503,
"learning_rate": 1.7502221591779932e-05,
"loss": 2.1541362762451173,
"step": 1220,
"token_acc": 0.5197708363379567
},
{
"epoch": 1.2760768033212246,
"grad_norm": 1.8829350471496582,
"learning_rate": 1.7457620949067263e-05,
"loss": 2.1336696624755858,
"step": 1230,
"token_acc": 0.5226117164876347
},
{
"epoch": 1.286455630513752,
"grad_norm": 1.6789767742156982,
"learning_rate": 1.7412683534967104e-05,
"loss": 2.088356781005859,
"step": 1240,
"token_acc": 0.5301837532884537
},
{
"epoch": 1.2968344577062791,
"grad_norm": 1.740821361541748,
"learning_rate": 1.736741137876405e-05,
"loss": 2.1419513702392576,
"step": 1250,
"token_acc": 0.5206938237049744
},
{
"epoch": 1.3072132848988065,
"grad_norm": 1.9089772701263428,
"learning_rate": 1.732180652485899e-05,
"loss": 2.106894683837891,
"step": 1260,
"token_acc": 0.5242820139727357
},
{
"epoch": 1.3175921120913336,
"grad_norm": 1.7507069110870361,
"learning_rate": 1.727587103267677e-05,
"loss": 2.1208877563476562,
"step": 1270,
"token_acc": 0.522964315558169
},
{
"epoch": 1.327970939283861,
"grad_norm": 1.8030635118484497,
"learning_rate": 1.7229606976573214e-05,
"loss": 2.1295166015625,
"step": 1280,
"token_acc": 0.5231044522938959
},
{
"epoch": 1.3383497664763881,
"grad_norm": 1.749598503112793,
"learning_rate": 1.7183016445741444e-05,
"loss": 2.1150535583496093,
"step": 1290,
"token_acc": 0.5260810499064414
},
{
"epoch": 1.3487285936689153,
"grad_norm": 1.841452717781067,
"learning_rate": 1.7136101544117526e-05,
"loss": 2.0860462188720703,
"step": 1300,
"token_acc": 0.5301403547828902
},
{
"epoch": 1.3591074208614426,
"grad_norm": 1.621980905532837,
"learning_rate": 1.708886439028547e-05,
"loss": 2.1209121704101563,
"step": 1310,
"token_acc": 0.5272716694625178
},
{
"epoch": 1.36948624805397,
"grad_norm": 1.8915696144104004,
"learning_rate": 1.704130711738157e-05,
"loss": 2.114282989501953,
"step": 1320,
"token_acc": 0.5247490268387626
},
{
"epoch": 1.3798650752464972,
"grad_norm": 1.8269680738449097,
"learning_rate": 1.699343187299804e-05,
"loss": 2.163526916503906,
"step": 1330,
"token_acc": 0.5173366466152501
},
{
"epoch": 1.3902439024390243,
"grad_norm": 1.8983516693115234,
"learning_rate": 1.6945240819086082e-05,
"loss": 2.0931949615478516,
"step": 1340,
"token_acc": 0.529971025880273
},
{
"epoch": 1.4006227296315517,
"grad_norm": 1.7726497650146484,
"learning_rate": 1.689673613185821e-05,
"loss": 2.1190900802612305,
"step": 1350,
"token_acc": 0.5240369229538363
},
{
"epoch": 1.411001556824079,
"grad_norm": 1.821448802947998,
"learning_rate": 1.6847920001690003e-05,
"loss": 2.1365760803222655,
"step": 1360,
"token_acc": 0.5210763622903032
},
{
"epoch": 1.4213803840166062,
"grad_norm": 1.82371985912323,
"learning_rate": 1.6798794633021192e-05,
"loss": 2.138067436218262,
"step": 1370,
"token_acc": 0.5223474543334629
},
{
"epoch": 1.4317592112091333,
"grad_norm": 1.7606170177459717,
"learning_rate": 1.67493622442561e-05,
"loss": 2.127475357055664,
"step": 1380,
"token_acc": 0.5230829895656394
},
{
"epoch": 1.4421380384016607,
"grad_norm": 1.9313206672668457,
"learning_rate": 1.669962506766347e-05,
"loss": 2.121912384033203,
"step": 1390,
"token_acc": 0.5240360124338542
},
{
"epoch": 1.4525168655941878,
"grad_norm": 1.847873568534851,
"learning_rate": 1.6649585349275662e-05,
"loss": 2.1304636001586914,
"step": 1400,
"token_acc": 0.521845779697262
},
{
"epoch": 1.4628956927867152,
"grad_norm": 1.826349139213562,
"learning_rate": 1.659924534878723e-05,
"loss": 2.1476728439331056,
"step": 1410,
"token_acc": 0.5234251464542264
},
{
"epoch": 1.4732745199792423,
"grad_norm": 1.8113420009613037,
"learning_rate": 1.6548607339452853e-05,
"loss": 2.1420124053955076,
"step": 1420,
"token_acc": 0.5214704018253264
},
{
"epoch": 1.4836533471717697,
"grad_norm": 1.878710150718689,
"learning_rate": 1.6497673607984717e-05,
"loss": 2.1145393371582033,
"step": 1430,
"token_acc": 0.5260452540787269
},
{
"epoch": 1.4940321743642968,
"grad_norm": 1.753811240196228,
"learning_rate": 1.6446446454449234e-05,
"loss": 2.0994091033935547,
"step": 1440,
"token_acc": 0.5279226115246548
},
{
"epoch": 1.5044110015568242,
"grad_norm": 1.816480278968811,
"learning_rate": 1.639492819216316e-05,
"loss": 2.0477016448974608,
"step": 1450,
"token_acc": 0.5362872382997907
},
{
"epoch": 1.5147898287493513,
"grad_norm": 1.746500015258789,
"learning_rate": 1.6343121147589162e-05,
"loss": 2.079163360595703,
"step": 1460,
"token_acc": 0.5300070198174848
},
{
"epoch": 1.5251686559418784,
"grad_norm": 1.7371795177459717,
"learning_rate": 1.6291027660230735e-05,
"loss": 2.092520904541016,
"step": 1470,
"token_acc": 0.5292052445162493
},
{
"epoch": 1.5355474831344058,
"grad_norm": 1.7395926713943481,
"learning_rate": 1.623865008252656e-05,
"loss": 2.1143264770507812,
"step": 1480,
"token_acc": 0.5241492663878434
},
{
"epoch": 1.5459263103269332,
"grad_norm": 1.7556476593017578,
"learning_rate": 1.6185990779744284e-05,
"loss": 2.097298812866211,
"step": 1490,
"token_acc": 0.5284930817610063
},
{
"epoch": 1.5563051375194603,
"grad_norm": 1.8573205471038818,
"learning_rate": 1.6133052129873693e-05,
"loss": 2.075461769104004,
"step": 1500,
"token_acc": 0.5315147157322406
},
{
"epoch": 1.5666839647119875,
"grad_norm": 1.762276291847229,
"learning_rate": 1.6079836523519335e-05,
"loss": 2.0853599548339843,
"step": 1510,
"token_acc": 0.529249945603183
},
{
"epoch": 1.5770627919045148,
"grad_norm": 1.8757967948913574,
"learning_rate": 1.6026346363792565e-05,
"loss": 2.077694320678711,
"step": 1520,
"token_acc": 0.5309355781832846
},
{
"epoch": 1.5874416190970422,
"grad_norm": 1.6929080486297607,
"learning_rate": 1.597258406620303e-05,
"loss": 2.0887657165527345,
"step": 1530,
"token_acc": 0.5275544046158739
},
{
"epoch": 1.5978204462895693,
"grad_norm": 1.7281657457351685,
"learning_rate": 1.5918552058549576e-05,
"loss": 2.0982549667358397,
"step": 1540,
"token_acc": 0.5289624380291547
},
{
"epoch": 1.6081992734820965,
"grad_norm": 1.725917100906372,
"learning_rate": 1.5864252780810616e-05,
"loss": 2.138423538208008,
"step": 1550,
"token_acc": 0.5216128402068746
},
{
"epoch": 1.6185781006746238,
"grad_norm": 1.7427935600280762,
"learning_rate": 1.5809688685033972e-05,
"loss": 2.0888511657714846,
"step": 1560,
"token_acc": 0.5288291381632815
},
{
"epoch": 1.628956927867151,
"grad_norm": 1.7530733346939087,
"learning_rate": 1.57548622352261e-05,
"loss": 2.0690521240234374,
"step": 1570,
"token_acc": 0.5308751620048847
},
{
"epoch": 1.6393357550596783,
"grad_norm": 1.7077672481536865,
"learning_rate": 1.5699775907240866e-05,
"loss": 2.0827823638916017,
"step": 1580,
"token_acc": 0.530173223707932
},
{
"epoch": 1.6497145822522055,
"grad_norm": 1.733396053314209,
"learning_rate": 1.5644432188667695e-05,
"loss": 2.1037742614746096,
"step": 1590,
"token_acc": 0.525743371335082
},
{
"epoch": 1.6600934094447326,
"grad_norm": 1.8180595636367798,
"learning_rate": 1.558883357871928e-05,
"loss": 2.0920333862304688,
"step": 1600,
"token_acc": 0.5262100813141768
},
{
"epoch": 1.67047223663726,
"grad_norm": 1.7032748460769653,
"learning_rate": 1.5532982588118698e-05,
"loss": 2.0978115081787108,
"step": 1610,
"token_acc": 0.5273756760053674
},
{
"epoch": 1.6808510638297873,
"grad_norm": 1.7440638542175293,
"learning_rate": 1.5476881738986037e-05,
"loss": 2.0799293518066406,
"step": 1620,
"token_acc": 0.5302636182479198
},
{
"epoch": 1.6912298910223145,
"grad_norm": 1.7569373846054077,
"learning_rate": 1.5420533564724495e-05,
"loss": 2.1291650772094726,
"step": 1630,
"token_acc": 0.5237950062498095
},
{
"epoch": 1.7016087182148416,
"grad_norm": 1.7734380960464478,
"learning_rate": 1.5363940609905996e-05,
"loss": 2.1278526306152346,
"step": 1640,
"token_acc": 0.5226562178616974
},
{
"epoch": 1.711987545407369,
"grad_norm": 1.6634830236434937,
"learning_rate": 1.5307105430156255e-05,
"loss": 2.0615726470947267,
"step": 1650,
"token_acc": 0.5319221878814638
},
{
"epoch": 1.7223663725998963,
"grad_norm": 1.721252679824829,
"learning_rate": 1.5250030592039396e-05,
"loss": 2.077913284301758,
"step": 1660,
"token_acc": 0.5318907975706068
},
{
"epoch": 1.7327451997924235,
"grad_norm": 1.7259483337402344,
"learning_rate": 1.519271867294203e-05,
"loss": 2.0709917068481447,
"step": 1670,
"token_acc": 0.5315355633729523
},
{
"epoch": 1.7431240269849506,
"grad_norm": 1.783433198928833,
"learning_rate": 1.5135172260956886e-05,
"loss": 2.133807373046875,
"step": 1680,
"token_acc": 0.523378414562062
},
{
"epoch": 1.753502854177478,
"grad_norm": 1.6700115203857422,
"learning_rate": 1.5077393954765917e-05,
"loss": 2.0949087142944336,
"step": 1690,
"token_acc": 0.5273437108462719
},
{
"epoch": 1.7638816813700053,
"grad_norm": 1.6670721769332886,
"learning_rate": 1.501938636352297e-05,
"loss": 2.0465778350830077,
"step": 1700,
"token_acc": 0.5351224052201545
},
{
"epoch": 1.7742605085625325,
"grad_norm": 1.6864069700241089,
"learning_rate": 1.4961152106735937e-05,
"loss": 2.106570816040039,
"step": 1710,
"token_acc": 0.5253623922959959
},
{
"epoch": 1.7846393357550596,
"grad_norm": 1.6960480213165283,
"learning_rate": 1.490269381414849e-05,
"loss": 2.084445571899414,
"step": 1720,
"token_acc": 0.5288636989164007
},
{
"epoch": 1.7950181629475868,
"grad_norm": 1.7800339460372925,
"learning_rate": 1.4844014125621307e-05,
"loss": 2.0880548477172853,
"step": 1730,
"token_acc": 0.5298676428051347
},
{
"epoch": 1.8053969901401141,
"grad_norm": 1.689630389213562,
"learning_rate": 1.4785115691012866e-05,
"loss": 2.078695297241211,
"step": 1740,
"token_acc": 0.5314548695380711
},
{
"epoch": 1.8157758173326415,
"grad_norm": 1.7510846853256226,
"learning_rate": 1.4726001170059795e-05,
"loss": 2.09201717376709,
"step": 1750,
"token_acc": 0.5283520961847461
},
{
"epoch": 1.8261546445251686,
"grad_norm": 1.7273612022399902,
"learning_rate": 1.4666673232256738e-05,
"loss": 2.0915267944335936,
"step": 1760,
"token_acc": 0.5283787368848153
},
{
"epoch": 1.8365334717176958,
"grad_norm": 1.7171927690505981,
"learning_rate": 1.4607134556735836e-05,
"loss": 2.0861387252807617,
"step": 1770,
"token_acc": 0.5299122815892512
},
{
"epoch": 1.8469122989102231,
"grad_norm": 1.8282674551010132,
"learning_rate": 1.4547387832145718e-05,
"loss": 2.086101531982422,
"step": 1780,
"token_acc": 0.5271156016001641
},
{
"epoch": 1.8572911261027505,
"grad_norm": 1.6166794300079346,
"learning_rate": 1.4487435756530101e-05,
"loss": 2.087788772583008,
"step": 1790,
"token_acc": 0.5281107055166977
},
{
"epoch": 1.8676699532952776,
"grad_norm": 1.831827163696289,
"learning_rate": 1.4427281037205944e-05,
"loss": 2.117390441894531,
"step": 1800,
"token_acc": 0.5241738597476888
},
{
"epoch": 1.8780487804878048,
"grad_norm": 1.7074508666992188,
"learning_rate": 1.4366926390641203e-05,
"loss": 2.0853967666625977,
"step": 1810,
"token_acc": 0.5279534725864675
},
{
"epoch": 1.8884276076803321,
"grad_norm": 1.8115159273147583,
"learning_rate": 1.4306374542332141e-05,
"loss": 2.088706207275391,
"step": 1820,
"token_acc": 0.5298170599136548
},
{
"epoch": 1.8988064348728595,
"grad_norm": 1.6567020416259766,
"learning_rate": 1.4245628226680267e-05,
"loss": 2.079012870788574,
"step": 1830,
"token_acc": 0.5316991760720085
},
{
"epoch": 1.9091852620653866,
"grad_norm": 1.701375961303711,
"learning_rate": 1.4184690186868849e-05,
"loss": 2.0808317184448244,
"step": 1840,
"token_acc": 0.5284962769859978
},
{
"epoch": 1.9195640892579138,
"grad_norm": 1.7267203330993652,
"learning_rate": 1.4123563174739036e-05,
"loss": 2.065626335144043,
"step": 1850,
"token_acc": 0.5311625273884282
},
{
"epoch": 1.9299429164504411,
"grad_norm": 1.6275725364685059,
"learning_rate": 1.40622499506656e-05,
"loss": 2.0688688278198244,
"step": 1860,
"token_acc": 0.5323680728339115
},
{
"epoch": 1.9403217436429685,
"grad_norm": 1.721309781074524,
"learning_rate": 1.4000753283432267e-05,
"loss": 2.0954654693603514,
"step": 1870,
"token_acc": 0.5289602926848667
},
{
"epoch": 1.9507005708354956,
"grad_norm": 1.6101154088974,
"learning_rate": 1.3939075950106698e-05,
"loss": 2.0555797576904298,
"step": 1880,
"token_acc": 0.5353732487628076
},
{
"epoch": 1.9610793980280228,
"grad_norm": 1.8473503589630127,
"learning_rate": 1.3877220735915072e-05,
"loss": 2.050533676147461,
"step": 1890,
"token_acc": 0.5320265148528384
},
{
"epoch": 1.97145822522055,
"grad_norm": 1.8174254894256592,
"learning_rate": 1.3815190434116317e-05,
"loss": 2.0770517349243165,
"step": 1900,
"token_acc": 0.5300979764710779
},
{
"epoch": 1.9818370524130773,
"grad_norm": 1.69548499584198,
"learning_rate": 1.3752987845875976e-05,
"loss": 2.07806282043457,
"step": 1910,
"token_acc": 0.5292110806322391
},
{
"epoch": 1.9922158796056046,
"grad_norm": 1.5917421579360962,
"learning_rate": 1.3690615780139703e-05,
"loss": 2.052938461303711,
"step": 1920,
"token_acc": 0.5370187115408765
},
{
"epoch": 2.0020757654385055,
"grad_norm": 1.7463245391845703,
"learning_rate": 1.362807705350641e-05,
"loss": 2.070224380493164,
"step": 1930,
"token_acc": 0.5304937076476283
},
{
"epoch": 2.0124545926310327,
"grad_norm": 1.7398828268051147,
"learning_rate": 1.3565374490101105e-05,
"loss": 1.987207794189453,
"step": 1940,
"token_acc": 0.5466110284338398
},
{
"epoch": 2.02283341982356,
"grad_norm": 1.7470279932022095,
"learning_rate": 1.3502510921447323e-05,
"loss": 1.937457275390625,
"step": 1950,
"token_acc": 0.5544097067217744
},
{
"epoch": 2.0332122470160874,
"grad_norm": 1.791390299797058,
"learning_rate": 1.3439489186339283e-05,
"loss": 1.9402462005615235,
"step": 1960,
"token_acc": 0.5536063560414234
},
{
"epoch": 2.0435910742086145,
"grad_norm": 1.6864056587219238,
"learning_rate": 1.337631213071369e-05,
"loss": 1.9131607055664062,
"step": 1970,
"token_acc": 0.5578064262674717
},
{
"epoch": 2.0539699014011417,
"grad_norm": 1.8310033082962036,
"learning_rate": 1.3312982607521212e-05,
"loss": 1.9271564483642578,
"step": 1980,
"token_acc": 0.5548212010050511
},
{
"epoch": 2.064348728593669,
"grad_norm": 1.8236348628997803,
"learning_rate": 1.3249503476597649e-05,
"loss": 1.926010513305664,
"step": 1990,
"token_acc": 0.5540556603529807
},
{
"epoch": 2.074727555786196,
"grad_norm": 1.708382248878479,
"learning_rate": 1.31858776045348e-05,
"loss": 1.9321002960205078,
"step": 2000,
"token_acc": 0.5518456998013848
},
{
"epoch": 2.0851063829787235,
"grad_norm": 1.6481667757034302,
"learning_rate": 1.3122107864550993e-05,
"loss": 1.927775764465332,
"step": 2010,
"token_acc": 0.5548617305976806
},
{
"epoch": 2.0954852101712507,
"grad_norm": 1.757744312286377,
"learning_rate": 1.3058197136361344e-05,
"loss": 1.889733123779297,
"step": 2020,
"token_acc": 0.561735058458638
},
{
"epoch": 2.105864037363778,
"grad_norm": 1.7434204816818237,
"learning_rate": 1.2994148306047726e-05,
"loss": 1.9208293914794923,
"step": 2030,
"token_acc": 0.5547297792385877
},
{
"epoch": 2.116242864556305,
"grad_norm": 1.8360788822174072,
"learning_rate": 1.292996426592843e-05,
"loss": 1.9793046951293944,
"step": 2040,
"token_acc": 0.544568625874407
},
{
"epoch": 2.1266216917488325,
"grad_norm": 1.7190735340118408,
"learning_rate": 1.2865647914427543e-05,
"loss": 1.8811424255371094,
"step": 2050,
"token_acc": 0.5606674976202122
},
{
"epoch": 2.1370005189413597,
"grad_norm": 1.6018221378326416,
"learning_rate": 1.2801202155944086e-05,
"loss": 1.9047758102416992,
"step": 2060,
"token_acc": 0.5577417115523959
},
{
"epoch": 2.147379346133887,
"grad_norm": 1.6971921920776367,
"learning_rate": 1.2736629900720832e-05,
"loss": 1.950063705444336,
"step": 2070,
"token_acc": 0.5499321369325894
},
{
"epoch": 2.157758173326414,
"grad_norm": 1.69591224193573,
"learning_rate": 1.2671934064712898e-05,
"loss": 1.9196895599365233,
"step": 2080,
"token_acc": 0.5539260475224423
},
{
"epoch": 2.1681370005189415,
"grad_norm": 1.7615793943405151,
"learning_rate": 1.2607117569456073e-05,
"loss": 1.94398193359375,
"step": 2090,
"token_acc": 0.5507702425821466
},
{
"epoch": 2.1785158277114687,
"grad_norm": 1.852057695388794,
"learning_rate": 1.2542183341934873e-05,
"loss": 1.9146221160888672,
"step": 2100,
"token_acc": 0.5536376236985462
},
{
"epoch": 2.188894654903996,
"grad_norm": 1.747358798980713,
"learning_rate": 1.247713431445036e-05,
"loss": 1.939622688293457,
"step": 2110,
"token_acc": 0.5543611504007544
},
{
"epoch": 2.199273482096523,
"grad_norm": 1.8548592329025269,
"learning_rate": 1.2411973424487751e-05,
"loss": 1.929229164123535,
"step": 2120,
"token_acc": 0.5530863176182252
},
{
"epoch": 2.2096523092890505,
"grad_norm": 1.7708196640014648,
"learning_rate": 1.2346703614583747e-05,
"loss": 1.944478988647461,
"step": 2130,
"token_acc": 0.5536431149607415
},
{
"epoch": 2.2200311364815777,
"grad_norm": 1.7282150983810425,
"learning_rate": 1.2281327832193648e-05,
"loss": 1.9053688049316406,
"step": 2140,
"token_acc": 0.5580555889784623
},
{
"epoch": 2.230409963674105,
"grad_norm": 1.6658769845962524,
"learning_rate": 1.2215849029558272e-05,
"loss": 1.9024145126342773,
"step": 2150,
"token_acc": 0.560320781032078
},
{
"epoch": 2.240788790866632,
"grad_norm": 1.7705820798873901,
"learning_rate": 1.2150270163570621e-05,
"loss": 1.9199504852294922,
"step": 2160,
"token_acc": 0.5565634842168564
},
{
"epoch": 2.251167618059159,
"grad_norm": 1.6693559885025024,
"learning_rate": 1.2084594195642367e-05,
"loss": 1.9336135864257813,
"step": 2170,
"token_acc": 0.5529033185182144
},
{
"epoch": 2.2615464452516867,
"grad_norm": 1.7091015577316284,
"learning_rate": 1.2018824091570103e-05,
"loss": 1.9000381469726562,
"step": 2180,
"token_acc": 0.5591887977828945
},
{
"epoch": 2.271925272444214,
"grad_norm": 1.7270673513412476,
"learning_rate": 1.1952962821401432e-05,
"loss": 1.9196353912353517,
"step": 2190,
"token_acc": 0.5560962629782574
},
{
"epoch": 2.282304099636741,
"grad_norm": 1.647047519683838,
"learning_rate": 1.1887013359300836e-05,
"loss": 1.9115699768066405,
"step": 2200,
"token_acc": 0.5580860008957423
},
{
"epoch": 2.292682926829268,
"grad_norm": 1.7045695781707764,
"learning_rate": 1.1820978683415368e-05,
"loss": 1.9291133880615234,
"step": 2210,
"token_acc": 0.5530297243482999
},
{
"epoch": 2.3030617540217957,
"grad_norm": 1.7511004209518433,
"learning_rate": 1.1754861775740163e-05,
"loss": 1.9382858276367188,
"step": 2220,
"token_acc": 0.5529861170215429
},
{
"epoch": 2.313440581214323,
"grad_norm": 1.599604606628418,
"learning_rate": 1.1688665621983787e-05,
"loss": 1.9184059143066405,
"step": 2230,
"token_acc": 0.556391511828612
},
{
"epoch": 2.32381940840685,
"grad_norm": 1.6984072923660278,
"learning_rate": 1.1622393211433405e-05,
"loss": 1.913759422302246,
"step": 2240,
"token_acc": 0.5549265670631057
},
{
"epoch": 2.334198235599377,
"grad_norm": 1.8092048168182373,
"learning_rate": 1.1556047536819776e-05,
"loss": 1.9401369094848633,
"step": 2250,
"token_acc": 0.5522028887793999
},
{
"epoch": 2.3445770627919047,
"grad_norm": 1.7931917905807495,
"learning_rate": 1.1489631594182129e-05,
"loss": 1.913161849975586,
"step": 2260,
"token_acc": 0.5568072732813572
},
{
"epoch": 2.354955889984432,
"grad_norm": 1.7338532209396362,
"learning_rate": 1.1423148382732854e-05,
"loss": 1.9345035552978516,
"step": 2270,
"token_acc": 0.5521660993733167
},
{
"epoch": 2.365334717176959,
"grad_norm": 1.7197600603103638,
"learning_rate": 1.1356600904722067e-05,
"loss": 1.9324146270751954,
"step": 2280,
"token_acc": 0.5531795485062101
},
{
"epoch": 2.375713544369486,
"grad_norm": 1.7181566953659058,
"learning_rate": 1.1289992165302036e-05,
"loss": 1.9197006225585938,
"step": 2290,
"token_acc": 0.5551382707152318
},
{
"epoch": 2.3860923715620137,
"grad_norm": 1.7071539163589478,
"learning_rate": 1.122332517239147e-05,
"loss": 1.902444839477539,
"step": 2300,
"token_acc": 0.55637035555228
},
{
"epoch": 2.396471198754541,
"grad_norm": 1.7314884662628174,
"learning_rate": 1.1156602936539696e-05,
"loss": 1.9253314971923827,
"step": 2310,
"token_acc": 0.5539153524050082
},
{
"epoch": 2.406850025947068,
"grad_norm": 1.740742564201355,
"learning_rate": 1.1089828470790694e-05,
"loss": 1.9190488815307618,
"step": 2320,
"token_acc": 0.5549246051671213
},
{
"epoch": 2.417228853139595,
"grad_norm": 1.8096532821655273,
"learning_rate": 1.1023004790547055e-05,
"loss": 1.9092010498046874,
"step": 2330,
"token_acc": 0.557160651433474
},
{
"epoch": 2.4276076803321223,
"grad_norm": 1.614668369293213,
"learning_rate": 1.0956134913433788e-05,
"loss": 1.928387451171875,
"step": 2340,
"token_acc": 0.5524327108821635
},
{
"epoch": 2.43798650752465,
"grad_norm": 1.6005795001983643,
"learning_rate": 1.0889221859162062e-05,
"loss": 1.9043733596801757,
"step": 2350,
"token_acc": 0.5570991503723802
},
{
"epoch": 2.448365334717177,
"grad_norm": 1.745969533920288,
"learning_rate": 1.082226864939285e-05,
"loss": 1.9200620651245117,
"step": 2360,
"token_acc": 0.5562498700326478
},
{
"epoch": 2.458744161909704,
"grad_norm": 1.816898226737976,
"learning_rate": 1.0755278307600459e-05,
"loss": 1.9352451324462892,
"step": 2370,
"token_acc": 0.5538184492860223
},
{
"epoch": 2.4691229891022313,
"grad_norm": 1.7103019952774048,
"learning_rate": 1.0688253858936002e-05,
"loss": 1.9363134384155274,
"step": 2380,
"token_acc": 0.5517950208675069
},
{
"epoch": 2.479501816294759,
"grad_norm": 1.7398525476455688,
"learning_rate": 1.0621198330090805e-05,
"loss": 1.9553054809570312,
"step": 2390,
"token_acc": 0.5484108066170879
},
{
"epoch": 2.489880643487286,
"grad_norm": 1.7609021663665771,
"learning_rate": 1.05541147491597e-05,
"loss": 1.9113622665405274,
"step": 2400,
"token_acc": 0.5569021208403235
},
{
"epoch": 2.500259470679813,
"grad_norm": 1.6799272298812866,
"learning_rate": 1.04870061455043e-05,
"loss": 1.883762741088867,
"step": 2410,
"token_acc": 0.5617027855799211
},
{
"epoch": 2.5106382978723403,
"grad_norm": 1.8168262243270874,
"learning_rate": 1.0419875549616196e-05,
"loss": 1.9137689590454101,
"step": 2420,
"token_acc": 0.5557871460236681
},
{
"epoch": 2.5210171250648674,
"grad_norm": 1.6799908876419067,
"learning_rate": 1.0352725992980104e-05,
"loss": 1.9013198852539062,
"step": 2430,
"token_acc": 0.5567794519651424
},
{
"epoch": 2.531395952257395,
"grad_norm": 1.7614784240722656,
"learning_rate": 1.0285560507936962e-05,
"loss": 1.9300392150878907,
"step": 2440,
"token_acc": 0.556598812423096
},
{
"epoch": 2.541774779449922,
"grad_norm": 1.7416421175003052,
"learning_rate": 1.0218382127547022e-05,
"loss": 1.9304391860961914,
"step": 2450,
"token_acc": 0.5545185709087368
},
{
"epoch": 2.5521536066424493,
"grad_norm": 1.6595633029937744,
"learning_rate": 1.0151193885452845e-05,
"loss": 1.9420501708984375,
"step": 2460,
"token_acc": 0.552393083334597
},
{
"epoch": 2.562532433834977,
"grad_norm": 1.6998454332351685,
"learning_rate": 1.0083998815742335e-05,
"loss": 1.9268463134765625,
"step": 2470,
"token_acc": 0.5534130706371475
},
{
"epoch": 2.572911261027504,
"grad_norm": 1.7023824453353882,
"learning_rate": 1.0016799952811722e-05,
"loss": 1.9064176559448243,
"step": 2480,
"token_acc": 0.5587350238248682
},
{
"epoch": 2.583290088220031,
"grad_norm": 1.7349321842193604,
"learning_rate": 9.949600331228523e-06,
"loss": 1.928802490234375,
"step": 2490,
"token_acc": 0.5534973355570924
},
{
"epoch": 2.5936689154125583,
"grad_norm": 1.7485408782958984,
"learning_rate": 9.882402985594514e-06,
"loss": 1.9113471984863282,
"step": 2500,
"token_acc": 0.5557637992041242
},
{
"epoch": 2.6040477426050854,
"grad_norm": 1.8012971878051758,
"learning_rate": 9.815210950408703e-06,
"loss": 1.9024391174316406,
"step": 2510,
"token_acc": 0.5563252183844836
},
{
"epoch": 2.614426569797613,
"grad_norm": 1.734852910041809,
"learning_rate": 9.748027259930276e-06,
"loss": 1.9226268768310546,
"step": 2520,
"token_acc": 0.553243728321368
},
{
"epoch": 2.62480539699014,
"grad_norm": 1.7272549867630005,
"learning_rate": 9.6808549480416e-06,
"loss": 1.912221336364746,
"step": 2530,
"token_acc": 0.5554663991975928
},
{
"epoch": 2.6351842241826673,
"grad_norm": 1.7384474277496338,
"learning_rate": 9.6136970481112e-06,
"loss": 1.8983772277832032,
"step": 2540,
"token_acc": 0.5575010620383972
},
{
"epoch": 2.645563051375195,
"grad_norm": 1.6821212768554688,
"learning_rate": 9.54655659285679e-06,
"loss": 1.9068862915039062,
"step": 2550,
"token_acc": 0.5582667806167054
},
{
"epoch": 2.655941878567722,
"grad_norm": 1.6929022073745728,
"learning_rate": 9.47943661420831e-06,
"loss": 1.9249227523803711,
"step": 2560,
"token_acc": 0.5550895998690778
},
{
"epoch": 2.666320705760249,
"grad_norm": 1.5699330568313599,
"learning_rate": 9.412340143171025e-06,
"loss": 1.9345794677734376,
"step": 2570,
"token_acc": 0.5546420775617618
},
{
"epoch": 2.6766995329527763,
"grad_norm": 1.6654072999954224,
"learning_rate": 9.345270209688639e-06,
"loss": 1.9140254974365234,
"step": 2580,
"token_acc": 0.5561770464549146
},
{
"epoch": 2.6870783601453034,
"grad_norm": 1.7323963642120361,
"learning_rate": 9.278229842506476e-06,
"loss": 1.891197395324707,
"step": 2590,
"token_acc": 0.559995923151404
},
{
"epoch": 2.6974571873378306,
"grad_norm": 1.6370705366134644,
"learning_rate": 9.211222069034696e-06,
"loss": 1.9491371154785155,
"step": 2600,
"token_acc": 0.5505838534326555
},
{
"epoch": 2.707836014530358,
"grad_norm": 1.6768380403518677,
"learning_rate": 9.144249915211605e-06,
"loss": 1.9355926513671875,
"step": 2610,
"token_acc": 0.5530301856585844
},
{
"epoch": 2.7182148417228853,
"grad_norm": 1.6993346214294434,
"learning_rate": 9.07731640536698e-06,
"loss": 1.8661931991577148,
"step": 2620,
"token_acc": 0.566435676477357
},
{
"epoch": 2.7285936689154124,
"grad_norm": 1.8695818185806274,
"learning_rate": 9.010424562085531e-06,
"loss": 1.9347620010375977,
"step": 2630,
"token_acc": 0.5513946774501753
},
{
"epoch": 2.73897249610794,
"grad_norm": 1.7306283712387085,
"learning_rate": 8.943577406070369e-06,
"loss": 1.9210147857666016,
"step": 2640,
"token_acc": 0.5563004959603232
},
{
"epoch": 2.749351323300467,
"grad_norm": 1.7726759910583496,
"learning_rate": 8.876777956006631e-06,
"loss": 1.9050409317016601,
"step": 2650,
"token_acc": 0.5590982656649617
},
{
"epoch": 2.7597301504929943,
"grad_norm": 1.6881150007247925,
"learning_rate": 8.810029228425143e-06,
"loss": 1.8932125091552734,
"step": 2660,
"token_acc": 0.5570060388511354
},
{
"epoch": 2.7701089776855214,
"grad_norm": 1.765500545501709,
"learning_rate": 8.743334237566202e-06,
"loss": 1.9176090240478516,
"step": 2670,
"token_acc": 0.554214403691372
},
{
"epoch": 2.7804878048780486,
"grad_norm": 1.6848795413970947,
"learning_rate": 8.67669599524347e-06,
"loss": 1.8865711212158203,
"step": 2680,
"token_acc": 0.562042711044617
},
{
"epoch": 2.790866632070576,
"grad_norm": 1.7397648096084595,
"learning_rate": 8.61011751070794e-06,
"loss": 1.9190990447998046,
"step": 2690,
"token_acc": 0.5526579636075706
},
{
"epoch": 2.8012454592631033,
"grad_norm": 1.68130362033844,
"learning_rate": 8.543601790512082e-06,
"loss": 1.8705915451049804,
"step": 2700,
"token_acc": 0.5634827796813697
},
{
"epoch": 2.8116242864556305,
"grad_norm": 1.6546133756637573,
"learning_rate": 8.477151838374038e-06,
"loss": 1.9126605987548828,
"step": 2710,
"token_acc": 0.5567444713738346
},
{
"epoch": 2.822003113648158,
"grad_norm": 1.6276742219924927,
"learning_rate": 8.410770655042003e-06,
"loss": 1.8713298797607423,
"step": 2720,
"token_acc": 0.565101467890801
},
{
"epoch": 2.832381940840685,
"grad_norm": 1.7484148740768433,
"learning_rate": 8.3444612381587e-06,
"loss": 1.9256477355957031,
"step": 2730,
"token_acc": 0.5560268203646488
},
{
"epoch": 2.8427607680332123,
"grad_norm": 1.6800369024276733,
"learning_rate": 8.278226582126038e-06,
"loss": 1.917556381225586,
"step": 2740,
"token_acc": 0.5568249221183801
},
{
"epoch": 2.8531395952257395,
"grad_norm": 1.6541880369186401,
"learning_rate": 8.212069677969852e-06,
"loss": 1.9023046493530273,
"step": 2750,
"token_acc": 0.5583130021289491
},
{
"epoch": 2.8635184224182666,
"grad_norm": 1.6244224309921265,
"learning_rate": 8.145993513204876e-06,
"loss": 1.8897109985351563,
"step": 2760,
"token_acc": 0.5602205321322208
},
{
"epoch": 2.8738972496107937,
"grad_norm": 1.7208482027053833,
"learning_rate": 8.0800010716998e-06,
"loss": 1.9432632446289062,
"step": 2770,
"token_acc": 0.5509531773420171
},
{
"epoch": 2.8842760768033213,
"grad_norm": 1.6855223178863525,
"learning_rate": 8.014095333542548e-06,
"loss": 1.895047378540039,
"step": 2780,
"token_acc": 0.5613392045711302
},
{
"epoch": 2.8946549039958485,
"grad_norm": 1.6913646459579468,
"learning_rate": 7.948279274905677e-06,
"loss": 1.8993762969970702,
"step": 2790,
"token_acc": 0.5579996054448609
},
{
"epoch": 2.9050337311883756,
"grad_norm": 1.6410419940948486,
"learning_rate": 7.882555867912018e-06,
"loss": 1.9352861404418946,
"step": 2800,
"token_acc": 0.5537088527185062
},
{
"epoch": 2.915412558380903,
"grad_norm": 1.6772572994232178,
"learning_rate": 7.81692808050041e-06,
"loss": 1.9284124374389648,
"step": 2810,
"token_acc": 0.5541538222417947
},
{
"epoch": 2.9257913855734303,
"grad_norm": 1.7049256563186646,
"learning_rate": 7.751398876291725e-06,
"loss": 1.937514877319336,
"step": 2820,
"token_acc": 0.5518980676004275
},
{
"epoch": 2.9361702127659575,
"grad_norm": 1.6900954246520996,
"learning_rate": 7.685971214454994e-06,
"loss": 1.8913965225219727,
"step": 2830,
"token_acc": 0.5604702567465811
},
{
"epoch": 2.9465490399584846,
"grad_norm": 1.7197011709213257,
"learning_rate": 7.620648049573815e-06,
"loss": 1.911862564086914,
"step": 2840,
"token_acc": 0.5571605795950774
},
{
"epoch": 2.9569278671510117,
"grad_norm": 1.758101463317871,
"learning_rate": 7.5554323315128905e-06,
"loss": 1.8751121520996095,
"step": 2850,
"token_acc": 0.5672182689906118
},
{
"epoch": 2.9673066943435393,
"grad_norm": 1.733535647392273,
"learning_rate": 7.490327005284852e-06,
"loss": 1.8596960067749024,
"step": 2860,
"token_acc": 0.5660323686613866
},
{
"epoch": 2.9776855215360665,
"grad_norm": 1.757304072380066,
"learning_rate": 7.425335010917244e-06,
"loss": 1.9053394317626953,
"step": 2870,
"token_acc": 0.5565210612478237
},
{
"epoch": 2.9880643487285936,
"grad_norm": 1.7628564834594727,
"learning_rate": 7.3604592833197785e-06,
"loss": 1.8903701782226563,
"step": 2880,
"token_acc": 0.5576756287944492
},
{
"epoch": 2.9984431759211208,
"grad_norm": 1.7401490211486816,
"learning_rate": 7.2957027521517876e-06,
"loss": 1.9200553894042969,
"step": 2890,
"token_acc": 0.5563947198675396
},
{
"epoch": 3.0083030617540216,
"grad_norm": 1.7933138608932495,
"learning_rate": 7.231068341689923e-06,
"loss": 1.7847864151000976,
"step": 2900,
"token_acc": 0.5815433614942374
},
{
"epoch": 3.018681888946549,
"grad_norm": 1.7872165441513062,
"learning_rate": 7.166558970696118e-06,
"loss": 1.7788661956787108,
"step": 2910,
"token_acc": 0.5808766554404801
},
{
"epoch": 3.0290607161390763,
"grad_norm": 1.7825837135314941,
"learning_rate": 7.102177552285753e-06,
"loss": 1.766078567504883,
"step": 2920,
"token_acc": 0.5815241849133316
},
{
"epoch": 3.0394395433316035,
"grad_norm": 1.7438377141952515,
"learning_rate": 7.037926993796148e-06,
"loss": 1.7677196502685546,
"step": 2930,
"token_acc": 0.5844153279554498
},
{
"epoch": 3.0498183705241306,
"grad_norm": 1.812364935874939,
"learning_rate": 6.973810196655226e-06,
"loss": 1.7670604705810546,
"step": 2940,
"token_acc": 0.5820803530270934
},
{
"epoch": 3.060197197716658,
"grad_norm": 1.7296171188354492,
"learning_rate": 6.909830056250527e-06,
"loss": 1.793588638305664,
"step": 2950,
"token_acc": 0.5778754471934219
},
{
"epoch": 3.0705760249091854,
"grad_norm": 1.7110881805419922,
"learning_rate": 6.845989461798434e-06,
"loss": 1.7946462631225586,
"step": 2960,
"token_acc": 0.5781437542176867
},
{
"epoch": 3.0809548521017125,
"grad_norm": 1.6934293508529663,
"learning_rate": 6.7822912962137225e-06,
"loss": 1.7851028442382812,
"step": 2970,
"token_acc": 0.5798904484087285
},
{
"epoch": 3.0913336792942396,
"grad_norm": 1.7866111993789673,
"learning_rate": 6.718738435979346e-06,
"loss": 1.7402740478515626,
"step": 2980,
"token_acc": 0.5871197279124806
},
{
"epoch": 3.101712506486767,
"grad_norm": 1.736386775970459,
"learning_rate": 6.655333751016573e-06,
"loss": 1.779799461364746,
"step": 2990,
"token_acc": 0.5803670175726048
},
{
"epoch": 3.1120913336792944,
"grad_norm": 1.6074467897415161,
"learning_rate": 6.592080104555357e-06,
"loss": 1.7721286773681642,
"step": 3000,
"token_acc": 0.5815654279239847
},
{
"epoch": 3.1224701608718215,
"grad_norm": 1.654293417930603,
"learning_rate": 6.528980353005065e-06,
"loss": 1.7722492218017578,
"step": 3010,
"token_acc": 0.5809519043090936
},
{
"epoch": 3.1328489880643486,
"grad_norm": 1.757063627243042,
"learning_rate": 6.466037345825462e-06,
"loss": 1.7850852966308595,
"step": 3020,
"token_acc": 0.5779664537307686
},
{
"epoch": 3.143227815256876,
"grad_norm": 1.6419646739959717,
"learning_rate": 6.403253925398059e-06,
"loss": 1.7818527221679688,
"step": 3030,
"token_acc": 0.580335255100174
},
{
"epoch": 3.1536066424494034,
"grad_norm": 1.7364999055862427,
"learning_rate": 6.340632926897733e-06,
"loss": 1.7778926849365235,
"step": 3040,
"token_acc": 0.5805299510234836
},
{
"epoch": 3.1639854696419305,
"grad_norm": 1.686894178390503,
"learning_rate": 6.278177178164722e-06,
"loss": 1.7976924896240234,
"step": 3050,
"token_acc": 0.5755041075429425
},
{
"epoch": 3.1743642968344576,
"grad_norm": 1.813187599182129,
"learning_rate": 6.215889499576898e-06,
"loss": 1.7882804870605469,
"step": 3060,
"token_acc": 0.5757798878168254
},
{
"epoch": 3.184743124026985,
"grad_norm": 1.938328504562378,
"learning_rate": 6.153772703922434e-06,
"loss": 1.8018409729003906,
"step": 3070,
"token_acc": 0.5758089953727078
},
{
"epoch": 3.1951219512195124,
"grad_norm": 1.7211450338363647,
"learning_rate": 6.091829596272754e-06,
"loss": 1.7908195495605468,
"step": 3080,
"token_acc": 0.5797552100562355
},
{
"epoch": 3.2055007784120395,
"grad_norm": 1.7885199785232544,
"learning_rate": 6.030062973855881e-06,
"loss": 1.7822357177734376,
"step": 3090,
"token_acc": 0.5781079138938358
},
{
"epoch": 3.2158796056045666,
"grad_norm": 1.7050336599349976,
"learning_rate": 5.968475625930125e-06,
"loss": 1.7774345397949218,
"step": 3100,
"token_acc": 0.5787688935756673
},
{
"epoch": 3.226258432797094,
"grad_norm": 1.7510007619857788,
"learning_rate": 5.907070333658092e-06,
"loss": 1.7928211212158203,
"step": 3110,
"token_acc": 0.5779202171781916
},
{
"epoch": 3.2366372599896214,
"grad_norm": 1.7525726556777954,
"learning_rate": 5.845849869981137e-06,
"loss": 1.7825614929199218,
"step": 3120,
"token_acc": 0.5797023776728157
},
{
"epoch": 3.2470160871821485,
"grad_norm": 1.694647192955017,
"learning_rate": 5.784816999494107e-06,
"loss": 1.7892009735107421,
"step": 3130,
"token_acc": 0.5793172105672105
},
{
"epoch": 3.2573949143746757,
"grad_norm": 1.6872886419296265,
"learning_rate": 5.72397447832053e-06,
"loss": 1.7687557220458985,
"step": 3140,
"token_acc": 0.5815162887834331
},
{
"epoch": 3.267773741567203,
"grad_norm": 1.766538381576538,
"learning_rate": 5.663325053988112e-06,
"loss": 1.7987842559814453,
"step": 3150,
"token_acc": 0.5771982496214624
},
{
"epoch": 3.2781525687597304,
"grad_norm": 1.8170520067214966,
"learning_rate": 5.602871465304712e-06,
"loss": 1.7943660736083984,
"step": 3160,
"token_acc": 0.5749129461509762
},
{
"epoch": 3.2885313959522575,
"grad_norm": 1.7518370151519775,
"learning_rate": 5.542616442234618e-06,
"loss": 1.7794151306152344,
"step": 3170,
"token_acc": 0.5811122822868042
},
{
"epoch": 3.2989102231447847,
"grad_norm": 1.72953462600708,
"learning_rate": 5.482562705775307e-06,
"loss": 1.7845090866088866,
"step": 3180,
"token_acc": 0.5807300771208226
},
{
"epoch": 3.309289050337312,
"grad_norm": 1.7175217866897583,
"learning_rate": 5.422712967834536e-06,
"loss": 1.746173095703125,
"step": 3190,
"token_acc": 0.5869713294940864
},
{
"epoch": 3.319667877529839,
"grad_norm": 1.7991154193878174,
"learning_rate": 5.3630699311079025e-06,
"loss": 1.7695350646972656,
"step": 3200,
"token_acc": 0.5825589706933524
},
{
"epoch": 3.3300467047223665,
"grad_norm": 1.7676479816436768,
"learning_rate": 5.303636288956784e-06,
"loss": 1.779949951171875,
"step": 3210,
"token_acc": 0.5806730122409199
},
{
"epoch": 3.3404255319148937,
"grad_norm": 1.6731163263320923,
"learning_rate": 5.244414725286717e-06,
"loss": 1.7868644714355468,
"step": 3220,
"token_acc": 0.577503006382782
},
{
"epoch": 3.350804359107421,
"grad_norm": 1.7500766515731812,
"learning_rate": 5.185407914426185e-06,
"loss": 1.787148666381836,
"step": 3230,
"token_acc": 0.5780114006598221
},
{
"epoch": 3.361183186299948,
"grad_norm": 1.6943732500076294,
"learning_rate": 5.1266185210058716e-06,
"loss": 1.7858871459960937,
"step": 3240,
"token_acc": 0.5804821423210479
},
{
"epoch": 3.3715620134924755,
"grad_norm": 1.7913635969161987,
"learning_rate": 5.0680491998383075e-06,
"loss": 1.7993558883666991,
"step": 3250,
"token_acc": 0.5766716288947418
},
{
"epoch": 3.3819408406850027,
"grad_norm": 1.7697553634643555,
"learning_rate": 5.009702595798007e-06,
"loss": 1.7874996185302734,
"step": 3260,
"token_acc": 0.5784962270571046
},
{
"epoch": 3.39231966787753,
"grad_norm": 1.8096823692321777,
"learning_rate": 4.951581343702014e-06,
"loss": 1.7859077453613281,
"step": 3270,
"token_acc": 0.5775580323472723
},
{
"epoch": 3.402698495070057,
"grad_norm": 1.7445858716964722,
"learning_rate": 4.893688068190933e-06,
"loss": 1.7741769790649413,
"step": 3280,
"token_acc": 0.5796821238864461
},
{
"epoch": 3.413077322262584,
"grad_norm": 1.74964439868927,
"learning_rate": 4.836025383610382e-06,
"loss": 1.7720981597900392,
"step": 3290,
"token_acc": 0.581970378565688
},
{
"epoch": 3.4234561494551117,
"grad_norm": 1.6911801099777222,
"learning_rate": 4.778595893892965e-06,
"loss": 1.7849388122558594,
"step": 3300,
"token_acc": 0.5775393743314663
},
{
"epoch": 3.433834976647639,
"grad_norm": 1.7003135681152344,
"learning_rate": 4.721402192440662e-06,
"loss": 1.7562515258789062,
"step": 3310,
"token_acc": 0.5862133103245173
},
{
"epoch": 3.444213803840166,
"grad_norm": 1.7339173555374146,
"learning_rate": 4.664446862007718e-06,
"loss": 1.771366500854492,
"step": 3320,
"token_acc": 0.5824997048724279
},
{
"epoch": 3.4545926310326935,
"grad_norm": 1.676377773284912,
"learning_rate": 4.607732474584021e-06,
"loss": 1.7776805877685546,
"step": 3330,
"token_acc": 0.5792565255451217
},
{
"epoch": 3.4649714582252207,
"grad_norm": 1.7419383525848389,
"learning_rate": 4.551261591278948e-06,
"loss": 1.819643783569336,
"step": 3340,
"token_acc": 0.572021428357658
},
{
"epoch": 3.475350285417748,
"grad_norm": 1.7194054126739502,
"learning_rate": 4.4950367622057175e-06,
"loss": 1.7884777069091797,
"step": 3350,
"token_acc": 0.5775204932749228
},
{
"epoch": 3.485729112610275,
"grad_norm": 1.7317556142807007,
"learning_rate": 4.439060526366214e-06,
"loss": 1.7950115203857422,
"step": 3360,
"token_acc": 0.5767983268722787
},
{
"epoch": 3.496107939802802,
"grad_norm": 1.7749775648117065,
"learning_rate": 4.383335411536357e-06,
"loss": 1.7846269607543945,
"step": 3370,
"token_acc": 0.577009900267448
},
{
"epoch": 3.5064867669953297,
"grad_norm": 1.7031441926956177,
"learning_rate": 4.327863934151927e-06,
"loss": 1.822881317138672,
"step": 3380,
"token_acc": 0.5740582341671794
},
{
"epoch": 3.516865594187857,
"grad_norm": 1.725158452987671,
"learning_rate": 4.272648599194948e-06,
"loss": 1.8034452438354491,
"step": 3390,
"token_acc": 0.5752027714670477
},
{
"epoch": 3.527244421380384,
"grad_norm": 1.7717089653015137,
"learning_rate": 4.217691900080561e-06,
"loss": 1.7635791778564454,
"step": 3400,
"token_acc": 0.5858324159647731
},
{
"epoch": 3.537623248572911,
"grad_norm": 1.7894845008850098,
"learning_rate": 4.162996318544421e-06,
"loss": 1.8027706146240234,
"step": 3410,
"token_acc": 0.5765381410803377
},
{
"epoch": 3.5480020757654387,
"grad_norm": 1.7400885820388794,
"learning_rate": 4.108564324530626e-06,
"loss": 1.7660438537597656,
"step": 3420,
"token_acc": 0.5813853899020284
},
{
"epoch": 3.558380902957966,
"grad_norm": 1.6926931142807007,
"learning_rate": 4.054398376080195e-06,
"loss": 1.765034294128418,
"step": 3430,
"token_acc": 0.5831922378919834
},
{
"epoch": 3.568759730150493,
"grad_norm": 1.7972161769866943,
"learning_rate": 4.000500919220042e-06,
"loss": 1.7922992706298828,
"step": 3440,
"token_acc": 0.5796203984871603
},
{
"epoch": 3.57913855734302,
"grad_norm": 1.7740036249160767,
"learning_rate": 3.946874387852545e-06,
"loss": 1.784423828125,
"step": 3450,
"token_acc": 0.5785921129951878
},
{
"epoch": 3.5895173845355473,
"grad_norm": 1.6737877130508423,
"learning_rate": 3.893521203645618e-06,
"loss": 1.7723068237304687,
"step": 3460,
"token_acc": 0.5793755710151437
},
{
"epoch": 3.599896211728075,
"grad_norm": 1.7076884508132935,
"learning_rate": 3.840443775923365e-06,
"loss": 1.7948810577392578,
"step": 3470,
"token_acc": 0.5774442144601075
},
{
"epoch": 3.610275038920602,
"grad_norm": 1.7473175525665283,
"learning_rate": 3.7876445015572595e-06,
"loss": 1.742638397216797,
"step": 3480,
"token_acc": 0.5880681233139068
},
{
"epoch": 3.620653866113129,
"grad_norm": 1.7900375127792358,
"learning_rate": 3.7351257648579363e-06,
"loss": 1.7668539047241212,
"step": 3490,
"token_acc": 0.5807464999605999
},
{
"epoch": 3.6310326933056567,
"grad_norm": 1.6722220182418823,
"learning_rate": 3.6828899374674933e-06,
"loss": 1.7775386810302733,
"step": 3500,
"token_acc": 0.5794847923620121
},
{
"epoch": 3.641411520498184,
"grad_norm": 1.6988933086395264,
"learning_rate": 3.630939378252409e-06,
"loss": 1.7848529815673828,
"step": 3510,
"token_acc": 0.578767413040557
},
{
"epoch": 3.651790347690711,
"grad_norm": 1.7073800563812256,
"learning_rate": 3.5792764331970187e-06,
"loss": 1.7846630096435547,
"step": 3520,
"token_acc": 0.577402894174943
},
{
"epoch": 3.662169174883238,
"grad_norm": 1.7581138610839844,
"learning_rate": 3.5279034352975694e-06,
"loss": 1.7899368286132813,
"step": 3530,
"token_acc": 0.5776512268731138
},
{
"epoch": 3.6725480020757653,
"grad_norm": 1.78201425075531,
"learning_rate": 3.4768227044568727e-06,
"loss": 1.7802978515625,
"step": 3540,
"token_acc": 0.5816299247686703
},
{
"epoch": 3.682926829268293,
"grad_norm": 1.7444225549697876,
"learning_rate": 3.4260365473795275e-06,
"loss": 1.786656951904297,
"step": 3550,
"token_acc": 0.5805562818985638
},
{
"epoch": 3.69330565646082,
"grad_norm": 1.6898013353347778,
"learning_rate": 3.3755472574677815e-06,
"loss": 1.7475749969482421,
"step": 3560,
"token_acc": 0.5867399708791484
},
{
"epoch": 3.703684483653347,
"grad_norm": 1.815169095993042,
"learning_rate": 3.3253571147179333e-06,
"loss": 1.7867530822753905,
"step": 3570,
"token_acc": 0.5789359537739405
},
{
"epoch": 3.7140633108458743,
"grad_norm": 1.8932245969772339,
"learning_rate": 3.2754683856173996e-06,
"loss": 1.765546989440918,
"step": 3580,
"token_acc": 0.5831094736110353
},
{
"epoch": 3.724442138038402,
"grad_norm": 1.8122197389602661,
"learning_rate": 3.225883323042349e-06,
"loss": 1.7789619445800782,
"step": 3590,
"token_acc": 0.5809870570338412
},
{
"epoch": 3.734820965230929,
"grad_norm": 1.7348006963729858,
"learning_rate": 3.1766041661559768e-06,
"loss": 1.8092857360839845,
"step": 3600,
"token_acc": 0.5745436694361454
},
{
"epoch": 3.745199792423456,
"grad_norm": 1.7380821704864502,
"learning_rate": 3.1276331403073733e-06,
"loss": 1.7682304382324219,
"step": 3610,
"token_acc": 0.5805616224648986
},
{
"epoch": 3.7555786196159833,
"grad_norm": 1.6613750457763672,
"learning_rate": 3.0789724569310532e-06,
"loss": 1.7744525909423827,
"step": 3620,
"token_acc": 0.5791571258061707
},
{
"epoch": 3.7659574468085104,
"grad_norm": 1.6839523315429688,
"learning_rate": 3.0306243134470668e-06,
"loss": 1.8063148498535155,
"step": 3630,
"token_acc": 0.576251360450805
},
{
"epoch": 3.776336274001038,
"grad_norm": 1.792040467262268,
"learning_rate": 2.9825908931617942e-06,
"loss": 1.7527238845825195,
"step": 3640,
"token_acc": 0.5845000155904088
},
{
"epoch": 3.786715101193565,
"grad_norm": 1.751470685005188,
"learning_rate": 2.9348743651693356e-06,
"loss": 1.7899675369262695,
"step": 3650,
"token_acc": 0.5776564975729986
},
{
"epoch": 3.7970939283860923,
"grad_norm": 1.724918007850647,
"learning_rate": 2.8874768842535626e-06,
"loss": 1.7680557250976563,
"step": 3660,
"token_acc": 0.5814622110729144
},
{
"epoch": 3.80747275557862,
"grad_norm": 1.5394452810287476,
"learning_rate": 2.8404005907908083e-06,
"loss": 1.7768871307373046,
"step": 3670,
"token_acc": 0.5859133747744135
},
{
"epoch": 3.817851582771147,
"grad_norm": 1.7015700340270996,
"learning_rate": 2.793647610653225e-06,
"loss": 1.7709339141845704,
"step": 3680,
"token_acc": 0.5816131952839303
},
{
"epoch": 3.828230409963674,
"grad_norm": 1.7198463678359985,
"learning_rate": 2.747220055112768e-06,
"loss": 1.7493492126464845,
"step": 3690,
"token_acc": 0.5874759494729798
},
{
"epoch": 3.8386092371562013,
"grad_norm": 1.631688117980957,
"learning_rate": 2.7011200207458676e-06,
"loss": 1.78626708984375,
"step": 3700,
"token_acc": 0.5804323872869886
},
{
"epoch": 3.8489880643487284,
"grad_norm": 1.6682333946228027,
"learning_rate": 2.655349589338746e-06,
"loss": 1.7783952713012696,
"step": 3710,
"token_acc": 0.5815845290081098
},
{
"epoch": 3.8593668915412556,
"grad_norm": 1.8272972106933594,
"learning_rate": 2.6099108277934105e-06,
"loss": 1.7815776824951173,
"step": 3720,
"token_acc": 0.5822206373060954
},
{
"epoch": 3.869745718733783,
"grad_norm": 1.649388313293457,
"learning_rate": 2.5648057880343068e-06,
"loss": 1.7444576263427733,
"step": 3730,
"token_acc": 0.585452577486445
},
{
"epoch": 3.8801245459263103,
"grad_norm": 1.6842070817947388,
"learning_rate": 2.5200365069156728e-06,
"loss": 1.7332420349121094,
"step": 3740,
"token_acc": 0.5904594885959988
},
{
"epoch": 3.8905033731188374,
"grad_norm": 1.6842021942138672,
"learning_rate": 2.4756050061295535e-06,
"loss": 1.7731719970703126,
"step": 3750,
"token_acc": 0.5820157956712175
},
{
"epoch": 3.900882200311365,
"grad_norm": 1.7146912813186646,
"learning_rate": 2.4315132921144946e-06,
"loss": 1.7766891479492188,
"step": 3760,
"token_acc": 0.5809164672838864
},
{
"epoch": 3.911261027503892,
"grad_norm": 1.8315688371658325,
"learning_rate": 2.3877633559649505e-06,
"loss": 1.7766403198242187,
"step": 3770,
"token_acc": 0.5827163089677545
},
{
"epoch": 3.9216398546964193,
"grad_norm": 1.6925230026245117,
"learning_rate": 2.344357173341364e-06,
"loss": 1.8139257431030273,
"step": 3780,
"token_acc": 0.5744653676778617
},
{
"epoch": 3.9320186818889464,
"grad_norm": 1.6660903692245483,
"learning_rate": 2.3012967043809507e-06,
"loss": 1.8107398986816405,
"step": 3790,
"token_acc": 0.5755519687549817
},
{
"epoch": 3.9423975090814736,
"grad_norm": 1.6355550289154053,
"learning_rate": 2.2585838936091753e-06,
"loss": 1.738602066040039,
"step": 3800,
"token_acc": 0.5867274569402229
},
{
"epoch": 3.952776336274001,
"grad_norm": 1.670543909072876,
"learning_rate": 2.2162206698519584e-06,
"loss": 1.7471502304077149,
"step": 3810,
"token_acc": 0.5860558505191971
},
{
"epoch": 3.9631551634665283,
"grad_norm": 1.6030086278915405,
"learning_rate": 2.1742089461485504e-06,
"loss": 1.7789886474609375,
"step": 3820,
"token_acc": 0.581808097615086
},
{
"epoch": 3.9735339906590554,
"grad_norm": 1.7222487926483154,
"learning_rate": 2.132550619665168e-06,
"loss": 1.7590545654296874,
"step": 3830,
"token_acc": 0.5814983220781373
},
{
"epoch": 3.983912817851583,
"grad_norm": 1.7116672992706299,
"learning_rate": 2.0912475716093016e-06,
"loss": 1.7779376983642579,
"step": 3840,
"token_acc": 0.5806435407299491
},
{
"epoch": 3.99429164504411,
"grad_norm": 1.6757533550262451,
"learning_rate": 2.0503016671447786e-06,
"loss": 1.7501903533935548,
"step": 3850,
"token_acc": 0.5844212269599975
},
{
"epoch": 4.004151530877011,
"grad_norm": 1.6910278797149658,
"learning_rate": 2.009714755307519e-06,
"loss": 1.742609405517578,
"step": 3860,
"token_acc": 0.588688524590164
},
{
"epoch": 4.014530358069538,
"grad_norm": 1.7896193265914917,
"learning_rate": 1.9694886689220592e-06,
"loss": 1.7103912353515625,
"step": 3870,
"token_acc": 0.5943016350768731
},
{
"epoch": 4.024909185262065,
"grad_norm": 1.6299549341201782,
"learning_rate": 1.929625224518761e-06,
"loss": 1.66673583984375,
"step": 3880,
"token_acc": 0.6008856410969241
},
{
"epoch": 4.0352880124545925,
"grad_norm": 1.8055658340454102,
"learning_rate": 1.8901262222518025e-06,
"loss": 1.709968376159668,
"step": 3890,
"token_acc": 0.5919140319861859
},
{
"epoch": 4.04566683964712,
"grad_norm": 1.6955589056015015,
"learning_rate": 1.8509934458178713e-06,
"loss": 1.6995389938354493,
"step": 3900,
"token_acc": 0.5971204228706649
},
{
"epoch": 4.056045666839647,
"grad_norm": 1.7214521169662476,
"learning_rate": 1.812228662375628e-06,
"loss": 1.6903017044067383,
"step": 3910,
"token_acc": 0.596530791043925
},
{
"epoch": 4.066424494032175,
"grad_norm": 1.8086495399475098,
"learning_rate": 1.773833622465888e-06,
"loss": 1.6978885650634765,
"step": 3920,
"token_acc": 0.5953170482049751
},
{
"epoch": 4.076803321224702,
"grad_norm": 1.7852308750152588,
"learning_rate": 1.7358100599325944e-06,
"loss": 1.7042343139648437,
"step": 3930,
"token_acc": 0.596890219382512
},
{
"epoch": 4.087182148417229,
"grad_norm": 1.6867796182632446,
"learning_rate": 1.6981596918444953e-06,
"loss": 1.692108154296875,
"step": 3940,
"token_acc": 0.5973590926113075
},
{
"epoch": 4.097560975609756,
"grad_norm": 1.7375496625900269,
"learning_rate": 1.6608842184176243e-06,
"loss": 1.684442138671875,
"step": 3950,
"token_acc": 0.5984781729782404
},
{
"epoch": 4.107939802802283,
"grad_norm": 1.8466476202011108,
"learning_rate": 1.623985322938516e-06,
"loss": 1.7386917114257812,
"step": 3960,
"token_acc": 0.5894643862576256
},
{
"epoch": 4.1183186299948105,
"grad_norm": 1.7492787837982178,
"learning_rate": 1.587464671688187e-06,
"loss": 1.7124431610107422,
"step": 3970,
"token_acc": 0.5941661102164264
},
{
"epoch": 4.128697457187338,
"grad_norm": 1.7667131423950195,
"learning_rate": 1.5513239138668979e-06,
"loss": 1.717066192626953,
"step": 3980,
"token_acc": 0.5924065062962455
},
{
"epoch": 4.139076284379865,
"grad_norm": 1.7511990070343018,
"learning_rate": 1.5155646815196679e-06,
"loss": 1.6888088226318358,
"step": 3990,
"token_acc": 0.5969850853692671
},
{
"epoch": 4.149455111572392,
"grad_norm": 1.7568092346191406,
"learning_rate": 1.48018858946259e-06,
"loss": 1.680096435546875,
"step": 4000,
"token_acc": 0.5987453460498802
},
{
"epoch": 4.15983393876492,
"grad_norm": 1.7091623544692993,
"learning_rate": 1.445197235209892e-06,
"loss": 1.7219488143920898,
"step": 4010,
"token_acc": 0.592944015782332
},
{
"epoch": 4.170212765957447,
"grad_norm": 1.8365898132324219,
"learning_rate": 1.4105921989018112e-06,
"loss": 1.7337966918945313,
"step": 4020,
"token_acc": 0.5892132925012415
},
{
"epoch": 4.180591593149974,
"grad_norm": 1.6755924224853516,
"learning_rate": 1.3763750432332302e-06,
"loss": 1.6933116912841797,
"step": 4030,
"token_acc": 0.5995327949735183
},
{
"epoch": 4.190970420342501,
"grad_norm": 1.7931687831878662,
"learning_rate": 1.3425473133831124e-06,
"loss": 1.6765281677246093,
"step": 4040,
"token_acc": 0.6010357255327339
},
{
"epoch": 4.2013492475350285,
"grad_norm": 1.6096997261047363,
"learning_rate": 1.3091105369447166e-06,
"loss": 1.7237010955810548,
"step": 4050,
"token_acc": 0.5905854791436366
},
{
"epoch": 4.211728074727556,
"grad_norm": 1.7379004955291748,
"learning_rate": 1.2760662238566278e-06,
"loss": 1.6687942504882813,
"step": 4060,
"token_acc": 0.6011614210691452
},
{
"epoch": 4.222106901920083,
"grad_norm": 1.7937663793563843,
"learning_rate": 1.2434158663345553e-06,
"loss": 1.673321533203125,
"step": 4070,
"token_acc": 0.6016861621748134
},
{
"epoch": 4.23248572911261,
"grad_norm": 1.8034650087356567,
"learning_rate": 1.2111609388039625e-06,
"loss": 1.7340202331542969,
"step": 4080,
"token_acc": 0.5876445274018769
},
{
"epoch": 4.242864556305138,
"grad_norm": 1.7721613645553589,
"learning_rate": 1.1793028978334742e-06,
"loss": 1.710007667541504,
"step": 4090,
"token_acc": 0.5947956680131843
},
{
"epoch": 4.253243383497665,
"grad_norm": 1.7631462812423706,
"learning_rate": 1.1478431820691083e-06,
"loss": 1.6774227142333984,
"step": 4100,
"token_acc": 0.6000717930309479
},
{
"epoch": 4.263622210690192,
"grad_norm": 1.7071177959442139,
"learning_rate": 1.116783212169299e-06,
"loss": 1.6625963211059571,
"step": 4110,
"token_acc": 0.6026242224292946
},
{
"epoch": 4.274001037882719,
"grad_norm": 1.8286573886871338,
"learning_rate": 1.086124390740757e-06,
"loss": 1.6820335388183594,
"step": 4120,
"token_acc": 0.6008151642611133
},
{
"epoch": 4.2843798650752465,
"grad_norm": 1.651700735092163,
"learning_rate": 1.0558681022751127e-06,
"loss": 1.6813400268554688,
"step": 4130,
"token_acc": 0.6001151099656707
},
{
"epoch": 4.294758692267774,
"grad_norm": 1.742108702659607,
"learning_rate": 1.0260157130864178e-06,
"loss": 1.6750873565673827,
"step": 4140,
"token_acc": 0.6007164232792602
},
{
"epoch": 4.305137519460301,
"grad_norm": 1.7463233470916748,
"learning_rate": 9.9656857124942e-07,
"loss": 1.6914520263671875,
"step": 4150,
"token_acc": 0.5961045910547944
},
{
"epoch": 4.315516346652828,
"grad_norm": 1.7035527229309082,
"learning_rate": 9.675280065387117e-07,
"loss": 1.7397287368774415,
"step": 4160,
"token_acc": 0.5893181536683043
},
{
"epoch": 4.325895173845355,
"grad_norm": 1.77140474319458,
"learning_rate": 9.388953303686587e-07,
"loss": 1.7106395721435548,
"step": 4170,
"token_acc": 0.5921493811308592
},
{
"epoch": 4.336274001037883,
"grad_norm": 1.7126872539520264,
"learning_rate": 9.106718357341915e-07,
"loss": 1.7010669708251953,
"step": 4180,
"token_acc": 0.5955515114750783
},
{
"epoch": 4.34665282823041,
"grad_norm": 1.796852946281433,
"learning_rate": 8.82858797152416e-07,
"loss": 1.7181104660034179,
"step": 4190,
"token_acc": 0.5900823619051568
},
{
"epoch": 4.357031655422937,
"grad_norm": 1.6908812522888184,
"learning_rate": 8.554574706050489e-07,
"loss": 1.692803955078125,
"step": 4200,
"token_acc": 0.5963465698752072
},
{
"epoch": 4.3674104826154645,
"grad_norm": 1.659064769744873,
"learning_rate": 8.284690934817163e-07,
"loss": 1.7040370941162108,
"step": 4210,
"token_acc": 0.5949970697695386
},
{
"epoch": 4.377789309807992,
"grad_norm": 1.7856544256210327,
"learning_rate": 8.018948845240538e-07,
"loss": 1.7089218139648437,
"step": 4220,
"token_acc": 0.5951604668678505
},
{
"epoch": 4.388168137000519,
"grad_norm": 1.859031319618225,
"learning_rate": 7.757360437706995e-07,
"loss": 1.7297183990478515,
"step": 4230,
"token_acc": 0.5902978210536332
},
{
"epoch": 4.398546964193046,
"grad_norm": 1.7074394226074219,
"learning_rate": 7.49993752503072e-07,
"loss": 1.729861068725586,
"step": 4240,
"token_acc": 0.5920085039952345
},
{
"epoch": 4.408925791385573,
"grad_norm": 1.738698959350586,
"learning_rate": 7.246691731920485e-07,
"loss": 1.6933917999267578,
"step": 4250,
"token_acc": 0.5974227581743239
},
{
"epoch": 4.419304618578101,
"grad_norm": 1.8904592990875244,
"learning_rate": 6.997634494454575e-07,
"loss": 1.7053550720214843,
"step": 4260,
"token_acc": 0.5967213114754099
},
{
"epoch": 4.429683445770628,
"grad_norm": 1.7518664598464966,
"learning_rate": 6.752777059564431e-07,
"loss": 1.7066520690917968,
"step": 4270,
"token_acc": 0.5938410363962532
},
{
"epoch": 4.440062272963155,
"grad_norm": 1.8016411066055298,
"learning_rate": 6.51213048452668e-07,
"loss": 1.7155086517333984,
"step": 4280,
"token_acc": 0.5924170376621474
},
{
"epoch": 4.4504411001556825,
"grad_norm": 1.6942793130874634,
"learning_rate": 6.275705636463969e-07,
"loss": 1.7269073486328126,
"step": 4290,
"token_acc": 0.5920985146629427
},
{
"epoch": 4.46081992734821,
"grad_norm": 1.653254508972168,
"learning_rate": 6.043513191853978e-07,
"loss": 1.7162269592285155,
"step": 4300,
"token_acc": 0.5923132785877884
},
{
"epoch": 4.471198754540737,
"grad_norm": 1.788749098777771,
"learning_rate": 5.815563636047539e-07,
"loss": 1.7156272888183595,
"step": 4310,
"token_acc": 0.5921776049196685
},
{
"epoch": 4.481577581733264,
"grad_norm": 1.8069233894348145,
"learning_rate": 5.591867262794969e-07,
"loss": 1.721381378173828,
"step": 4320,
"token_acc": 0.5925161499198195
},
{
"epoch": 4.491956408925791,
"grad_norm": 1.6404447555541992,
"learning_rate": 5.372434173781338e-07,
"loss": 1.675924301147461,
"step": 4330,
"token_acc": 0.5985891250350865
},
{
"epoch": 4.502335236118318,
"grad_norm": 1.727259874343872,
"learning_rate": 5.157274278170188e-07,
"loss": 1.698771095275879,
"step": 4340,
"token_acc": 0.5971852415367059
},
{
"epoch": 4.512714063310846,
"grad_norm": 1.731723427772522,
"learning_rate": 4.946397292156157e-07,
"loss": 1.7040802001953126,
"step": 4350,
"token_acc": 0.5962499043342943
},
{
"epoch": 4.523092890503373,
"grad_norm": 1.6307471990585327,
"learning_rate": 4.739812738526151e-07,
"loss": 1.7101400375366211,
"step": 4360,
"token_acc": 0.5958292869920777
},
{
"epoch": 4.5334717176959005,
"grad_norm": 1.7450075149536133,
"learning_rate": 4.537529946229369e-07,
"loss": 1.7206541061401368,
"step": 4370,
"token_acc": 0.5935436913109443
},
{
"epoch": 4.543850544888428,
"grad_norm": 1.8258659839630127,
"learning_rate": 4.3395580499559276e-07,
"loss": 1.6948991775512696,
"step": 4380,
"token_acc": 0.5983454585760061
},
{
"epoch": 4.554229372080955,
"grad_norm": 1.7573914527893066,
"learning_rate": 4.1459059897244524e-07,
"loss": 1.708029556274414,
"step": 4390,
"token_acc": 0.5935960338314994
},
{
"epoch": 4.564608199273482,
"grad_norm": 1.7217154502868652,
"learning_rate": 3.956582510478368e-07,
"loss": 1.6753950119018555,
"step": 4400,
"token_acc": 0.6009915479497058
},
{
"epoch": 4.574987026466009,
"grad_norm": 1.7759228944778442,
"learning_rate": 3.7715961616908716e-07,
"loss": 1.7161563873291015,
"step": 4410,
"token_acc": 0.5936897584184406
},
{
"epoch": 4.585365853658536,
"grad_norm": 1.6017059087753296,
"learning_rate": 3.5909552969790376e-07,
"loss": 1.6627635955810547,
"step": 4420,
"token_acc": 0.6015646673694723
},
{
"epoch": 4.595744680851064,
"grad_norm": 1.8440685272216797,
"learning_rate": 3.4146680737264125e-07,
"loss": 1.7209892272949219,
"step": 4430,
"token_acc": 0.5906698414687637
},
{
"epoch": 4.606123508043591,
"grad_norm": 1.6559165716171265,
"learning_rate": 3.2427424527147647e-07,
"loss": 1.6923173904418944,
"step": 4440,
"token_acc": 0.5959501510649956
},
{
"epoch": 4.6165023352361185,
"grad_norm": 1.8385257720947266,
"learning_rate": 3.0751861977645124e-07,
"loss": 1.7102893829345702,
"step": 4450,
"token_acc": 0.5937051258868454
},
{
"epoch": 4.626881162428646,
"grad_norm": 1.6878036260604858,
"learning_rate": 2.912006875384199e-07,
"loss": 1.7114158630371095,
"step": 4460,
"token_acc": 0.5917366228115186
},
{
"epoch": 4.637259989621173,
"grad_norm": 1.728395938873291,
"learning_rate": 2.753211854428728e-07,
"loss": 1.6825084686279297,
"step": 4470,
"token_acc": 0.5977566663402012
},
{
"epoch": 4.6476388168137,
"grad_norm": 1.7561081647872925,
"learning_rate": 2.5988083057666534e-07,
"loss": 1.6936420440673827,
"step": 4480,
"token_acc": 0.5972652753687681
},
{
"epoch": 4.658017644006227,
"grad_norm": 1.770182728767395,
"learning_rate": 2.44880320195634e-07,
"loss": 1.7172508239746094,
"step": 4490,
"token_acc": 0.5923068507993728
},
{
"epoch": 4.668396471198754,
"grad_norm": 1.7293405532836914,
"learning_rate": 2.303203316931102e-07,
"loss": 1.721797561645508,
"step": 4500,
"token_acc": 0.5908964576942237
},
{
"epoch": 4.678775298391281,
"grad_norm": 1.745667815208435,
"learning_rate": 2.1620152256932703e-07,
"loss": 1.7090343475341796,
"step": 4510,
"token_acc": 0.5943612792230598
},
{
"epoch": 4.689154125583809,
"grad_norm": 1.7014964818954468,
"learning_rate": 2.0252453040173646e-07,
"loss": 1.6774726867675782,
"step": 4520,
"token_acc": 0.5988728151053164
},
{
"epoch": 4.6995329527763365,
"grad_norm": 1.7573457956314087,
"learning_rate": 1.8928997281620675e-07,
"loss": 1.7255043029785155,
"step": 4530,
"token_acc": 0.5909050964336854
},
{
"epoch": 4.709911779968864,
"grad_norm": 1.7178244590759277,
"learning_rate": 1.7649844745913914e-07,
"loss": 1.6658166885375976,
"step": 4540,
"token_acc": 0.6010626621432847
},
{
"epoch": 4.720290607161391,
"grad_norm": 1.824478268623352,
"learning_rate": 1.6415053197047724e-07,
"loss": 1.6976356506347656,
"step": 4550,
"token_acc": 0.5948620938326313
},
{
"epoch": 4.730669434353918,
"grad_norm": 1.7294687032699585,
"learning_rate": 1.522467839576214e-07,
"loss": 1.7149528503417968,
"step": 4560,
"token_acc": 0.5918517196542845
},
{
"epoch": 4.741048261546445,
"grad_norm": 1.7639027833938599,
"learning_rate": 1.407877409702496e-07,
"loss": 1.6906970977783202,
"step": 4570,
"token_acc": 0.5972861932095143
},
{
"epoch": 4.751427088738972,
"grad_norm": 1.648666262626648,
"learning_rate": 1.2977392047604065e-07,
"loss": 1.6744407653808593,
"step": 4580,
"token_acc": 0.6009719086082612
},
{
"epoch": 4.761805915931499,
"grad_norm": 1.6566241979599,
"learning_rate": 1.1920581983730805e-07,
"loss": 1.7074642181396484,
"step": 4590,
"token_acc": 0.5942052996756735
},
{
"epoch": 4.772184743124027,
"grad_norm": 1.6671931743621826,
"learning_rate": 1.0908391628854042e-07,
"loss": 1.7061281204223633,
"step": 4600,
"token_acc": 0.5962743325988282
},
{
"epoch": 4.7825635703165545,
"grad_norm": 1.7677408456802368,
"learning_rate": 9.940866691484863e-08,
"loss": 1.7212074279785157,
"step": 4610,
"token_acc": 0.5918779311845147
},
{
"epoch": 4.792942397509082,
"grad_norm": 1.7271703481674194,
"learning_rate": 9.018050863132566e-08,
"loss": 1.6927852630615234,
"step": 4620,
"token_acc": 0.5969355987586983
},
{
"epoch": 4.803321224701609,
"grad_norm": 1.682909607887268,
"learning_rate": 8.139985816331908e-08,
"loss": 1.69879150390625,
"step": 4630,
"token_acc": 0.5959208358532668
},
{
"epoch": 4.813700051894136,
"grad_norm": 1.689661979675293,
"learning_rate": 7.306711202760718e-08,
"loss": 1.7013179779052734,
"step": 4640,
"token_acc": 0.5961094642433302
},
{
"epoch": 4.824078879086663,
"grad_norm": 1.6871150732040405,
"learning_rate": 6.51826465144978e-08,
"loss": 1.714627456665039,
"step": 4650,
"token_acc": 0.5948218898299994
},
{
"epoch": 4.83445770627919,
"grad_norm": 1.7642101049423218,
"learning_rate": 5.77468176708329e-08,
"loss": 1.6921161651611327,
"step": 4660,
"token_acc": 0.5985717377191084
},
{
"epoch": 4.844836533471717,
"grad_norm": 1.6736119985580444,
"learning_rate": 5.0759961283911584e-08,
"loss": 1.7187393188476563,
"step": 4670,
"token_acc": 0.5924537922243467
},
{
"epoch": 4.8552153606642445,
"grad_norm": 1.7387622594833374,
"learning_rate": 4.4222392866325456e-08,
"loss": 1.6748529434204102,
"step": 4680,
"token_acc": 0.5991042175151463
},
{
"epoch": 4.865594187856773,
"grad_norm": 1.6944735050201416,
"learning_rate": 3.81344076417145e-08,
"loss": 1.7051300048828124,
"step": 4690,
"token_acc": 0.5982032816096221
},
{
"epoch": 4.8759730150493,
"grad_norm": 1.7164373397827148,
"learning_rate": 3.2496280531428834e-08,
"loss": 1.7267358779907227,
"step": 4700,
"token_acc": 0.589399637620476
},
{
"epoch": 4.886351842241827,
"grad_norm": 1.7054399251937866,
"learning_rate": 2.7308266142119788e-08,
"loss": 1.6742828369140625,
"step": 4710,
"token_acc": 0.6011013249834184
},
{
"epoch": 4.896730669434354,
"grad_norm": 1.6896377801895142,
"learning_rate": 2.257059875423795e-08,
"loss": 1.7254058837890625,
"step": 4720,
"token_acc": 0.591559245127359
},
{
"epoch": 4.907109496626881,
"grad_norm": 1.768836498260498,
"learning_rate": 1.8283492311457208e-08,
"loss": 1.686863899230957,
"step": 4730,
"token_acc": 0.5981005486484064
},
{
"epoch": 4.917488323819408,
"grad_norm": 1.7688549757003784,
"learning_rate": 1.4447140411011362e-08,
"loss": 1.6876266479492188,
"step": 4740,
"token_acc": 0.5960698121363951
},
{
"epoch": 4.927867151011935,
"grad_norm": 1.7029192447662354,
"learning_rate": 1.1061716294951118e-08,
"loss": 1.7269210815429688,
"step": 4750,
"token_acc": 0.5908425521236329
},
{
"epoch": 4.9382459782044625,
"grad_norm": 1.6509218215942383,
"learning_rate": 8.127372842323677e-09,
"loss": 1.6810314178466796,
"step": 4760,
"token_acc": 0.5996703955253696
},
{
"epoch": 4.948624805396991,
"grad_norm": 1.7697540521621704,
"learning_rate": 5.644242562264923e-09,
"loss": 1.703883743286133,
"step": 4770,
"token_acc": 0.5973025239252244
},
{
"epoch": 4.959003632589518,
"grad_norm": 1.7465263605117798,
"learning_rate": 3.612437588018658e-09,
"loss": 1.66983642578125,
"step": 4780,
"token_acc": 0.6020027753039372
},
{
"epoch": 4.969382459782045,
"grad_norm": 1.7069917917251587,
"learning_rate": 2.032049671873981e-09,
"loss": 1.6933467864990235,
"step": 4790,
"token_acc": 0.5969661586365126
},
{
"epoch": 4.979761286974572,
"grad_norm": 1.8520318269729614,
"learning_rate": 9.03150181017498e-10,
"loss": 1.6973377227783204,
"step": 4800,
"token_acc": 0.5973939669670745
},
{
"epoch": 4.990140114167099,
"grad_norm": 1.7904108762741089,
"learning_rate": 2.2579009431256128e-10,
"loss": 1.7138263702392578,
"step": 4810,
"token_acc": 0.5927531382450163
},
{
"epoch": 5.0,
"grad_norm": 2.6223461627960205,
"learning_rate": 0.0,
"loss": 1.6906837463378905,
"step": 4820,
"token_acc": 0.5991248737798721
}
],
"logging_steps": 10,
"max_steps": 4820,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"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": 1.6373275083470275e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}