{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7636967349197565,
  "eval_steps": 500,
  "global_step": 345,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011068068622025456,
      "grad_norm": 13.653609275817871,
      "learning_rate": 2.162496240601504e-06,
      "loss": 0.4322,
      "mean_token_accuracy": 0.8802119046449661,
      "num_tokens": 840803.0,
      "step": 5
    },
    {
      "epoch": 0.02213613724405091,
      "grad_norm": 2.2131333351135254,
      "learning_rate": 4.865616541353383e-06,
      "loss": 0.2425,
      "mean_token_accuracy": 0.9426376819610596,
      "num_tokens": 1682100.0,
      "step": 10
    },
    {
      "epoch": 0.03320420586607637,
      "grad_norm": 1.3403221368789673,
      "learning_rate": 7.568736842105265e-06,
      "loss": 0.1813,
      "mean_token_accuracy": 0.9479484707117081,
      "num_tokens": 2522198.0,
      "step": 15
    },
    {
      "epoch": 0.04427227448810182,
      "grad_norm": 1.0376732349395752,
      "learning_rate": 1.0271857142857143e-05,
      "loss": 0.1473,
      "mean_token_accuracy": 0.9570796817541123,
      "num_tokens": 3370961.0,
      "step": 20
    },
    {
      "epoch": 0.05534034311012728,
      "grad_norm": 0.9869170188903809,
      "learning_rate": 1.2974977443609024e-05,
      "loss": 0.1445,
      "mean_token_accuracy": 0.958665081858635,
      "num_tokens": 4201807.0,
      "step": 25
    },
    {
      "epoch": 0.06640841173215274,
      "grad_norm": 1.0934088230133057,
      "learning_rate": 1.5678097744360906e-05,
      "loss": 0.1414,
      "mean_token_accuracy": 0.9576921403408051,
      "num_tokens": 5053890.0,
      "step": 30
    },
    {
      "epoch": 0.0774764803541782,
      "grad_norm": 0.95280921459198,
      "learning_rate": 1.8381218045112784e-05,
      "loss": 0.1301,
      "mean_token_accuracy": 0.9617523699998856,
      "num_tokens": 5902468.0,
      "step": 35
    },
    {
      "epoch": 0.08854454897620365,
      "grad_norm": 1.0132145881652832,
      "learning_rate": 1.8918604941067526e-05,
      "loss": 0.1202,
      "mean_token_accuracy": 0.9646110743284225,
      "num_tokens": 6744845.0,
      "step": 40
    },
    {
      "epoch": 0.0996126175982291,
      "grad_norm": 0.7649837732315063,
      "learning_rate": 1.8905459023589886e-05,
      "loss": 0.1332,
      "mean_token_accuracy": 0.9595840632915497,
      "num_tokens": 7582042.0,
      "step": 45
    },
    {
      "epoch": 0.11068068622025456,
      "grad_norm": 0.746411144733429,
      "learning_rate": 1.8882220756628106e-05,
      "loss": 0.1407,
      "mean_token_accuracy": 0.9589782208204269,
      "num_tokens": 8428895.0,
      "step": 50
    },
    {
      "epoch": 0.12174875484228002,
      "grad_norm": 0.5607208609580994,
      "learning_rate": 1.8848923268945807e-05,
      "loss": 0.126,
      "mean_token_accuracy": 0.9630925774574279,
      "num_tokens": 9268492.0,
      "step": 55
    },
    {
      "epoch": 0.13281682346430548,
      "grad_norm": 0.6422283053398132,
      "learning_rate": 1.8805614029857285e-05,
      "loss": 0.1385,
      "mean_token_accuracy": 0.9596903711557389,
      "num_tokens": 10116266.0,
      "step": 60
    },
    {
      "epoch": 0.14388489208633093,
      "grad_norm": 0.6571022868156433,
      "learning_rate": 1.8752354781554696e-05,
      "loss": 0.1288,
      "mean_token_accuracy": 0.964001452922821,
      "num_tokens": 10952744.0,
      "step": 65
    },
    {
      "epoch": 0.1549529607083564,
      "grad_norm": 0.9449382424354553,
      "learning_rate": 1.8689221451087584e-05,
      "loss": 0.1438,
      "mean_token_accuracy": 0.9580135941505432,
      "num_tokens": 11814719.0,
      "step": 70
    },
    {
      "epoch": 0.16602102933038185,
      "grad_norm": 0.5420695543289185,
      "learning_rate": 1.8616304042120364e-05,
      "loss": 0.15,
      "mean_token_accuracy": 0.9571842730045319,
      "num_tokens": 12659194.0,
      "step": 75
    },
    {
      "epoch": 0.1770890979524073,
      "grad_norm": 0.809925377368927,
      "learning_rate": 1.8533706506621947e-05,
      "loss": 0.1376,
      "mean_token_accuracy": 0.9587794840335846,
      "num_tokens": 13510515.0,
      "step": 80
    },
    {
      "epoch": 0.18815716657443277,
      "grad_norm": 0.6338202357292175,
      "learning_rate": 1.8441546596670535e-05,
      "loss": 0.1619,
      "mean_token_accuracy": 0.9550160259008408,
      "num_tokens": 14338019.0,
      "step": 85
    },
    {
      "epoch": 0.1992252351964582,
      "grad_norm": 0.5862089395523071,
      "learning_rate": 1.8339955696584762e-05,
      "loss": 0.1119,
      "mean_token_accuracy": 0.9656822383403778,
      "num_tokens": 15193682.0,
      "step": 90
    },
    {
      "epoch": 0.21029330381848368,
      "grad_norm": 0.648704469203949,
      "learning_rate": 1.8229078635620596e-05,
      "loss": 0.1312,
      "mean_token_accuracy": 0.962630569934845,
      "num_tokens": 16035737.0,
      "step": 95
    },
    {
      "epoch": 0.22136137244050913,
      "grad_norm": 0.7342209219932556,
      "learning_rate": 1.810907348150093e-05,
      "loss": 0.128,
      "mean_token_accuracy": 0.9622824192047119,
      "num_tokens": 16880634.0,
      "step": 100
    },
    {
      "epoch": 0.23242944106253458,
      "grad_norm": 0.546590268611908,
      "learning_rate": 1.7980111315072266e-05,
      "loss": 0.1123,
      "mean_token_accuracy": 0.964433366060257,
      "num_tokens": 17734618.0,
      "step": 105
    },
    {
      "epoch": 0.24349750968456005,
      "grad_norm": 0.6802765727043152,
      "learning_rate": 1.7842375986409714e-05,
      "loss": 0.1214,
      "mean_token_accuracy": 0.9634374409914017,
      "num_tokens": 18582745.0,
      "step": 110
    },
    {
      "epoch": 0.2545655783065855,
      "grad_norm": 0.4863690137863159,
      "learning_rate": 1.7696063852718036e-05,
      "loss": 0.1276,
      "mean_token_accuracy": 0.96299709379673,
      "num_tokens": 19427599.0,
      "step": 115
    },
    {
      "epoch": 0.26563364692861097,
      "grad_norm": 0.5270338654518127,
      "learning_rate": 1.754138349840237e-05,
      "loss": 0.1315,
      "mean_token_accuracy": 0.9605427175760269,
      "num_tokens": 20265496.0,
      "step": 120
    },
    {
      "epoch": 0.27670171555063644,
      "grad_norm": 0.6099231839179993,
      "learning_rate": 1.7378555437707684e-05,
      "loss": 0.1064,
      "mean_token_accuracy": 0.9678303599357605,
      "num_tokens": 21101798.0,
      "step": 125
    },
    {
      "epoch": 0.28776978417266186,
      "grad_norm": 0.606917142868042,
      "learning_rate": 1.7207811800350917e-05,
      "loss": 0.1431,
      "mean_token_accuracy": 0.9589549630880356,
      "num_tokens": 21941144.0,
      "step": 130
    },
    {
      "epoch": 0.29883785279468733,
      "grad_norm": 0.36009252071380615,
      "learning_rate": 1.702939600059396e-05,
      "loss": 0.1091,
      "mean_token_accuracy": 0.9663841336965561,
      "num_tokens": 22771309.0,
      "step": 135
    },
    {
      "epoch": 0.3099059214167128,
      "grad_norm": 0.6717250347137451,
      "learning_rate": 1.6843562390229243e-05,
      "loss": 0.1235,
      "mean_token_accuracy": 0.9656095921993255,
      "num_tokens": 23621859.0,
      "step": 140
    },
    {
      "epoch": 0.3209739900387382,
      "grad_norm": 0.6852691173553467,
      "learning_rate": 1.6650575895972645e-05,
      "loss": 0.1072,
      "mean_token_accuracy": 0.9671792030334473,
      "num_tokens": 24457970.0,
      "step": 145
    },
    {
      "epoch": 0.3320420586607637,
      "grad_norm": 0.6916231513023376,
      "learning_rate": 1.645071164178065e-05,
      "loss": 0.1243,
      "mean_token_accuracy": 0.9641483157873154,
      "num_tokens": 25293105.0,
      "step": 150
    },
    {
      "epoch": 0.34311012728278917,
      "grad_norm": 0.5273182988166809,
      "learning_rate": 1.624425455663021e-05,
      "loss": 0.1123,
      "mean_token_accuracy": 0.9667149662971497,
      "num_tokens": 26139993.0,
      "step": 155
    },
    {
      "epoch": 0.3541781959048146,
      "grad_norm": 0.6902707815170288,
      "learning_rate": 1.603149896832042e-05,
      "loss": 0.1243,
      "mean_token_accuracy": 0.9622602194547654,
      "num_tokens": 26976907.0,
      "step": 160
    },
    {
      "epoch": 0.36524626452684006,
      "grad_norm": 0.5414988994598389,
      "learning_rate": 1.581274818387516e-05,
      "loss": 0.1095,
      "mean_token_accuracy": 0.9667827695608139,
      "num_tokens": 27818759.0,
      "step": 165
    },
    {
      "epoch": 0.37631433314886553,
      "grad_norm": 0.5219632387161255,
      "learning_rate": 1.5588314057144782e-05,
      "loss": 0.1391,
      "mean_token_accuracy": 0.961360877752304,
      "num_tokens": 28667127.0,
      "step": 170
    },
    {
      "epoch": 0.387382401770891,
      "grad_norm": 0.5299946665763855,
      "learning_rate": 1.5358516544223398e-05,
      "loss": 0.1196,
      "mean_token_accuracy": 0.9628437578678131,
      "num_tokens": 29513406.0,
      "step": 175
    },
    {
      "epoch": 0.3984504703929164,
      "grad_norm": 0.5977985262870789,
      "learning_rate": 1.5123683247315437e-05,
      "loss": 0.1167,
      "mean_token_accuracy": 0.9651520103216171,
      "num_tokens": 30347686.0,
      "step": 180
    },
    {
      "epoch": 0.4095185390149419,
      "grad_norm": 0.47220319509506226,
      "learning_rate": 1.4884148947701893e-05,
      "loss": 0.1201,
      "mean_token_accuracy": 0.9635279923677444,
      "num_tokens": 31193902.0,
      "step": 185
    },
    {
      "epoch": 0.42058660763696737,
      "grad_norm": 0.707006573677063,
      "learning_rate": 1.4640255128471913e-05,
      "loss": 0.113,
      "mean_token_accuracy": 0.9671693831682205,
      "num_tokens": 32016726.0,
      "step": 190
    },
    {
      "epoch": 0.4316546762589928,
      "grad_norm": 0.5363844633102417,
      "learning_rate": 1.4392349487700268e-05,
      "loss": 0.1156,
      "mean_token_accuracy": 0.966980305314064,
      "num_tokens": 32869380.0,
      "step": 195
    },
    {
      "epoch": 0.44272274488101826,
      "grad_norm": 0.5774763822555542,
      "learning_rate": 1.4140785442764624e-05,
      "loss": 0.1455,
      "mean_token_accuracy": 0.9601777195930481,
      "num_tokens": 33709768.0,
      "step": 200
    },
    {
      "epoch": 0.45379081350304373,
      "grad_norm": 0.8255547285079956,
      "learning_rate": 1.3885921626509305e-05,
      "loss": 0.1256,
      "mean_token_accuracy": 0.964248651266098,
      "num_tokens": 34552882.0,
      "step": 205
    },
    {
      "epoch": 0.46485888212506915,
      "grad_norm": 0.5388986468315125,
      "learning_rate": 1.362812137597385e-05,
      "loss": 0.1068,
      "mean_token_accuracy": 0.9669350922107697,
      "num_tokens": 35391309.0,
      "step": 210
    },
    {
      "epoch": 0.4759269507470946,
      "grad_norm": 0.5983878374099731,
      "learning_rate": 1.3367752214415174e-05,
      "loss": 0.1077,
      "mean_token_accuracy": 0.9662021070718765,
      "num_tokens": 36231175.0,
      "step": 215
    },
    {
      "epoch": 0.4869950193691201,
      "grad_norm": 0.48292040824890137,
      "learning_rate": 1.3105185327361837e-05,
      "loss": 0.1091,
      "mean_token_accuracy": 0.9656137079000473,
      "num_tokens": 37070888.0,
      "step": 220
    },
    {
      "epoch": 0.49806308799114557,
      "grad_norm": 0.5879212021827698,
      "learning_rate": 1.284079503344731e-05,
      "loss": 0.1203,
      "mean_token_accuracy": 0.9630721986293793,
      "num_tokens": 37916221.0,
      "step": 225
    },
    {
      "epoch": 0.509131156613171,
      "grad_norm": 0.567933201789856,
      "learning_rate": 1.2574958250776656e-05,
      "loss": 0.1006,
      "mean_token_accuracy": 0.9688385397195816,
      "num_tokens": 38762415.0,
      "step": 230
    },
    {
      "epoch": 0.5201992252351965,
      "grad_norm": 0.4535607397556305,
      "learning_rate": 1.230805395958738e-05,
      "loss": 0.1158,
      "mean_token_accuracy": 0.9657712131738663,
      "num_tokens": 39600524.0,
      "step": 235
    },
    {
      "epoch": 0.5312672938572219,
      "grad_norm": 0.6382467746734619,
      "learning_rate": 1.204046266197046e-05,
      "loss": 0.1068,
      "mean_token_accuracy": 0.9666551351547241,
      "num_tokens": 40428593.0,
      "step": 240
    },
    {
      "epoch": 0.5423353624792474,
      "grad_norm": 0.6708046793937683,
      "learning_rate": 1.1772565839421815e-05,
      "loss": 0.1029,
      "mean_token_accuracy": 0.9665695130825043,
      "num_tokens": 41292040.0,
      "step": 245
    },
    {
      "epoch": 0.5534034311012729,
      "grad_norm": 0.4944695234298706,
      "learning_rate": 1.150474540899753e-05,
      "loss": 0.1116,
      "mean_token_accuracy": 0.9655242592096329,
      "num_tokens": 42135257.0,
      "step": 250
    },
    {
      "epoch": 0.5644714997232982,
      "grad_norm": 0.46505752205848694,
      "learning_rate": 1.1237383178848112e-05,
      "loss": 0.1284,
      "mean_token_accuracy": 0.9615936934947967,
      "num_tokens": 42976210.0,
      "step": 255
    },
    {
      "epoch": 0.5755395683453237,
      "grad_norm": 0.5889484882354736,
      "learning_rate": 1.0970860303908045e-05,
      "loss": 0.1188,
      "mean_token_accuracy": 0.9643084704875946,
      "num_tokens": 43815813.0,
      "step": 260
    },
    {
      "epoch": 0.5866076369673492,
      "grad_norm": 0.6604783535003662,
      "learning_rate": 1.0705556742516538e-05,
      "loss": 0.1156,
      "mean_token_accuracy": 0.9643748074769973,
      "num_tokens": 44669092.0,
      "step": 265
    },
    {
      "epoch": 0.5976757055893747,
      "grad_norm": 0.5499563813209534,
      "learning_rate": 1.0441850714744179e-05,
      "loss": 0.1219,
      "mean_token_accuracy": 0.9653939753770828,
      "num_tokens": 45512420.0,
      "step": 270
    },
    {
      "epoch": 0.6087437742114001,
      "grad_norm": 0.5853216052055359,
      "learning_rate": 1.0180118163197672e-05,
      "loss": 0.1213,
      "mean_token_accuracy": 0.9646226286888122,
      "num_tokens": 46346879.0,
      "step": 275
    },
    {
      "epoch": 0.6198118428334256,
      "grad_norm": 0.5788092017173767,
      "learning_rate": 9.920732217071372e-06,
      "loss": 0.115,
      "mean_token_accuracy": 0.9655275106430053,
      "num_tokens": 47194175.0,
      "step": 280
    },
    {
      "epoch": 0.630879911455451,
      "grad_norm": 0.6205952167510986,
      "learning_rate": 9.664062660209635e-06,
      "loss": 0.1042,
      "mean_token_accuracy": 0.9677371174097061,
      "num_tokens": 48034628.0,
      "step": 285
    },
    {
      "epoch": 0.6419479800774764,
      "grad_norm": 0.6505280137062073,
      "learning_rate": 9.410475403938355e-06,
      "loss": 0.1157,
      "mean_token_accuracy": 0.9660432875156403,
      "num_tokens": 48873067.0,
      "step": 290
    },
    {
      "epoch": 0.6530160486995019,
      "grad_norm": 0.5844290852546692,
      "learning_rate": 9.160331965417215e-06,
      "loss": 0.1124,
      "mean_token_accuracy": 0.9670364469289779,
      "num_tokens": 49711026.0,
      "step": 295
    },
    {
      "epoch": 0.6640841173215274,
      "grad_norm": 0.705653727054596,
      "learning_rate": 8.913988952256295e-06,
      "loss": 0.1064,
      "mean_token_accuracy": 0.9672520190477372,
      "num_tokens": 50543146.0,
      "step": 300
    },
    {
      "epoch": 0.6751521859435529,
      "grad_norm": 0.6059849858283997,
      "learning_rate": 8.671797554131816e-06,
      "loss": 0.1047,
      "mean_token_accuracy": 0.9690884202718735,
      "num_tokens": 51386337.0,
      "step": 305
    },
    {
      "epoch": 0.6862202545655783,
      "grad_norm": 0.47822269797325134,
      "learning_rate": 8.43410304212576e-06,
      "loss": 0.1457,
      "mean_token_accuracy": 0.9591602087020874,
      "num_tokens": 52232844.0,
      "step": 310
    },
    {
      "epoch": 0.6972883231876038,
      "grad_norm": 0.6385252475738525,
      "learning_rate": 8.201244276503093e-06,
      "loss": 0.1242,
      "mean_token_accuracy": 0.9647625982761383,
      "num_tokens": 53081382.0,
      "step": 315
    },
    {
      "epoch": 0.7083563918096292,
      "grad_norm": 0.5775324702262878,
      "learning_rate": 7.97355322362833e-06,
      "loss": 0.1093,
      "mean_token_accuracy": 0.9659038871526718,
      "num_tokens": 53924276.0,
      "step": 320
    },
    {
      "epoch": 0.7194244604316546,
      "grad_norm": 0.41972240805625916,
      "learning_rate": 7.751354482710171e-06,
      "loss": 0.0902,
      "mean_token_accuracy": 0.9724017709493638,
      "num_tokens": 54768837.0,
      "step": 325
    },
    {
      "epoch": 0.7304925290536801,
      "grad_norm": 0.45390570163726807,
      "learning_rate": 7.53496482304878e-06,
      "loss": 0.0962,
      "mean_token_accuracy": 0.9697568625211715,
      "num_tokens": 55602955.0,
      "step": 330
    },
    {
      "epoch": 0.7415605976757056,
      "grad_norm": 0.5724795460700989,
      "learning_rate": 7.324692732445534e-06,
      "loss": 0.1046,
      "mean_token_accuracy": 0.9690662533044815,
      "num_tokens": 56451885.0,
      "step": 335
    },
    {
      "epoch": 0.7526286662977311,
      "grad_norm": 0.5892515182495117,
      "learning_rate": 7.120837977418959e-06,
      "loss": 0.1097,
      "mean_token_accuracy": 0.9660208851099015,
      "num_tokens": 57297421.0,
      "step": 340
    },
    {
      "epoch": 0.7636967349197565,
      "grad_norm": 0.45424604415893555,
      "learning_rate": 6.9236911758538305e-06,
      "loss": 0.0866,
      "mean_token_accuracy": 0.9710287392139435,
      "num_tokens": 58148483.0,
      "step": 345
    }
  ],
  "logging_steps": 5,
  "max_steps": 451,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.4747041639531807e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}