{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7249466950959488,
  "eval_steps": 500,
  "global_step": 255,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014214641080312722,
      "grad_norm": 6.871182441711426,
      "learning_rate": 6.3922857142857155e-06,
      "loss": 0.2485,
      "mean_token_accuracy": 0.9450622588396073,
      "num_tokens": 887206.0,
      "step": 5
    },
    {
      "epoch": 0.028429282160625444,
      "grad_norm": 1.325594425201416,
      "learning_rate": 1.438264285714286e-05,
      "loss": 0.1082,
      "mean_token_accuracy": 0.9722226887941361,
      "num_tokens": 1794305.0,
      "step": 10
    },
    {
      "epoch": 0.042643923240938165,
      "grad_norm": 0.5087984204292297,
      "learning_rate": 2.2373000000000008e-05,
      "loss": 0.081,
      "mean_token_accuracy": 0.977224838733673,
      "num_tokens": 2709233.0,
      "step": 15
    },
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 0.4056396186351776,
      "learning_rate": 3.036335714285715e-05,
      "loss": 0.078,
      "mean_token_accuracy": 0.9777782618999481,
      "num_tokens": 3593059.0,
      "step": 20
    },
    {
      "epoch": 0.07107320540156362,
      "grad_norm": 0.3569645583629608,
      "learning_rate": 3.835371428571429e-05,
      "loss": 0.0589,
      "mean_token_accuracy": 0.982857757806778,
      "num_tokens": 4490661.0,
      "step": 25
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 0.26100024580955505,
      "learning_rate": 4.634407142857144e-05,
      "loss": 0.0476,
      "mean_token_accuracy": 0.9861888229846955,
      "num_tokens": 5390703.0,
      "step": 30
    },
    {
      "epoch": 0.09950248756218906,
      "grad_norm": 0.3945460021495819,
      "learning_rate": 5.433442857142858e-05,
      "loss": 0.0624,
      "mean_token_accuracy": 0.9822388887405396,
      "num_tokens": 6292901.0,
      "step": 35
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 0.24367931485176086,
      "learning_rate": 5.591591735390603e-05,
      "loss": 0.0553,
      "mean_token_accuracy": 0.9845600903034211,
      "num_tokens": 7198746.0,
      "step": 40
    },
    {
      "epoch": 0.1279317697228145,
      "grad_norm": 0.1666172593832016,
      "learning_rate": 5.584859529021029e-05,
      "loss": 0.0438,
      "mean_token_accuracy": 0.9872712701559067,
      "num_tokens": 8114170.0,
      "step": 45
    },
    {
      "epoch": 0.14214641080312723,
      "grad_norm": 0.22081473469734192,
      "learning_rate": 5.5729663581302464e-05,
      "loss": 0.0414,
      "mean_token_accuracy": 0.9883612394332886,
      "num_tokens": 9008010.0,
      "step": 50
    },
    {
      "epoch": 0.15636105188343993,
      "grad_norm": 0.2508990168571472,
      "learning_rate": 5.5559416042084716e-05,
      "loss": 0.0401,
      "mean_token_accuracy": 0.9878490805625916,
      "num_tokens": 9928017.0,
      "step": 55
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 0.1963493824005127,
      "learning_rate": 5.5338273260678846e-05,
      "loss": 0.0507,
      "mean_token_accuracy": 0.9856410056352616,
      "num_tokens": 10837026.0,
      "step": 60
    },
    {
      "epoch": 0.1847903340440654,
      "grad_norm": 0.2281191349029541,
      "learning_rate": 5.506678155938425e-05,
      "loss": 0.0509,
      "mean_token_accuracy": 0.9851306498050689,
      "num_tokens": 11742665.0,
      "step": 65
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 0.256953626871109,
      "learning_rate": 5.474561164501562e-05,
      "loss": 0.0591,
      "mean_token_accuracy": 0.9836829543113709,
      "num_tokens": 12655033.0,
      "step": 70
    },
    {
      "epoch": 0.21321961620469082,
      "grad_norm": 0.2751316726207733,
      "learning_rate": 5.437555695195499e-05,
      "loss": 0.0575,
      "mean_token_accuracy": 0.9837276339530945,
      "num_tokens": 13544799.0,
      "step": 75
    },
    {
      "epoch": 0.22743425728500355,
      "grad_norm": 0.2688603401184082,
      "learning_rate": 5.3957531682011343e-05,
      "loss": 0.0439,
      "mean_token_accuracy": 0.9870765119791031,
      "num_tokens": 14462599.0,
      "step": 80
    },
    {
      "epoch": 0.24164889836531628,
      "grad_norm": 0.21777455508708954,
      "learning_rate": 5.349256854593028e-05,
      "loss": 0.0485,
      "mean_token_accuracy": 0.9861204415559769,
      "num_tokens": 15339976.0,
      "step": 85
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 0.17083778977394104,
      "learning_rate": 5.298181621213322e-05,
      "loss": 0.0579,
      "mean_token_accuracy": 0.9853537321090698,
      "num_tokens": 16238340.0,
      "step": 90
    },
    {
      "epoch": 0.27007818052594174,
      "grad_norm": 0.5376266837120056,
      "learning_rate": 5.2426536468988904e-05,
      "loss": 0.0466,
      "mean_token_accuracy": 0.9857672184705735,
      "num_tokens": 17141598.0,
      "step": 95
    },
    {
      "epoch": 0.28429282160625446,
      "grad_norm": 0.16752442717552185,
      "learning_rate": 5.1828101107627654e-05,
      "loss": 0.0394,
      "mean_token_accuracy": 0.9883748948574066,
      "num_tokens": 18045706.0,
      "step": 100
    },
    {
      "epoch": 0.29850746268656714,
      "grad_norm": 0.38392144441604614,
      "learning_rate": 5.118798853299927e-05,
      "loss": 0.0458,
      "mean_token_accuracy": 0.9867590636014938,
      "num_tokens": 18957181.0,
      "step": 105
    },
    {
      "epoch": 0.31272210376687987,
      "grad_norm": 0.24077363312244415,
      "learning_rate": 5.0507780111546755e-05,
      "loss": 0.0407,
      "mean_token_accuracy": 0.9889020144939422,
      "num_tokens": 19869157.0,
      "step": 110
    },
    {
      "epoch": 0.3269367448471926,
      "grad_norm": 0.7112686038017273,
      "learning_rate": 4.978915626451872e-05,
      "loss": 0.0354,
      "mean_token_accuracy": 0.989764729142189,
      "num_tokens": 20751402.0,
      "step": 115
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 0.16634443402290344,
      "learning_rate": 4.903389231657195e-05,
      "loss": 0.0407,
      "mean_token_accuracy": 0.98702851831913,
      "num_tokens": 21641637.0,
      "step": 120
    },
    {
      "epoch": 0.35536602700781805,
      "grad_norm": 0.20308031141757965,
      "learning_rate": 4.824385410991952e-05,
      "loss": 0.0488,
      "mean_token_accuracy": 0.9860991269350052,
      "num_tokens": 22535035.0,
      "step": 125
    },
    {
      "epoch": 0.3695806680881308,
      "grad_norm": 0.2445092499256134,
      "learning_rate": 4.742099339486009e-05,
      "loss": 0.0349,
      "mean_token_accuracy": 0.9901248484849929,
      "num_tokens": 23438890.0,
      "step": 130
    },
    {
      "epoch": 0.3837953091684435,
      "grad_norm": 0.20196396112442017,
      "learning_rate": 4.656734300807523e-05,
      "loss": 0.048,
      "mean_token_accuracy": 0.9866506159305573,
      "num_tokens": 24323116.0,
      "step": 135
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 0.2281273603439331,
      "learning_rate": 4.568501185060708e-05,
      "loss": 0.0398,
      "mean_token_accuracy": 0.987074014544487,
      "num_tokens": 25211409.0,
      "step": 140
    },
    {
      "epoch": 0.41222459132906897,
      "grad_norm": 0.11974825710058212,
      "learning_rate": 4.4776179677922605e-05,
      "loss": 0.0424,
      "mean_token_accuracy": 0.9883939027786255,
      "num_tokens": 26116136.0,
      "step": 145
    },
    {
      "epoch": 0.42643923240938164,
      "grad_norm": 0.22993908822536469,
      "learning_rate": 4.384309171493564e-05,
      "loss": 0.0489,
      "mean_token_accuracy": 0.9855056792497635,
      "num_tokens": 27037315.0,
      "step": 150
    },
    {
      "epoch": 0.44065387348969437,
      "grad_norm": 0.14406248927116394,
      "learning_rate": 4.288805310928974e-05,
      "loss": 0.0465,
      "mean_token_accuracy": 0.9867871999740601,
      "num_tokens": 27935052.0,
      "step": 155
    },
    {
      "epoch": 0.4548685145700071,
      "grad_norm": 0.24493859708309174,
      "learning_rate": 4.191342323660509e-05,
      "loss": 0.0385,
      "mean_token_accuracy": 0.9880851775407791,
      "num_tokens": 28841875.0,
      "step": 160
    },
    {
      "epoch": 0.4690831556503198,
      "grad_norm": 0.13263005018234253,
      "learning_rate": 4.092160987175766e-05,
      "loss": 0.0425,
      "mean_token_accuracy": 0.9889453381299973,
      "num_tokens": 29746494.0,
      "step": 165
    },
    {
      "epoch": 0.48329779673063256,
      "grad_norm": 0.20041435956954956,
      "learning_rate": 3.991506324059065e-05,
      "loss": 0.041,
      "mean_token_accuracy": 0.9881613284349442,
      "num_tokens": 30656198.0,
      "step": 170
    },
    {
      "epoch": 0.4975124378109453,
      "grad_norm": 0.1819387674331665,
      "learning_rate": 3.889626996675263e-05,
      "loss": 0.0372,
      "mean_token_accuracy": 0.9892402857542038,
      "num_tokens": 31569720.0,
      "step": 175
    },
    {
      "epoch": 0.511727078891258,
      "grad_norm": 0.17630170285701752,
      "learning_rate": 3.7867746928616975e-05,
      "loss": 0.032,
      "mean_token_accuracy": 0.9905756890773774,
      "num_tokens": 32475165.0,
      "step": 180
    },
    {
      "epoch": 0.5259417199715707,
      "grad_norm": 0.16773319244384766,
      "learning_rate": 3.68320350414583e-05,
      "loss": 0.0394,
      "mean_token_accuracy": 0.9884531736373902,
      "num_tokens": 33371947.0,
      "step": 185
    },
    {
      "epoch": 0.5401563610518835,
      "grad_norm": 0.16546893119812012,
      "learning_rate": 3.579169298024706e-05,
      "loss": 0.038,
      "mean_token_accuracy": 0.9890659153461456,
      "num_tokens": 34287276.0,
      "step": 190
    },
    {
      "epoch": 0.5543710021321961,
      "grad_norm": 0.23278185725212097,
      "learning_rate": 3.474929085856958e-05,
      "loss": 0.0478,
      "mean_token_accuracy": 0.9864420264959335,
      "num_tokens": 35177015.0,
      "step": 195
    },
    {
      "epoch": 0.5685856432125089,
      "grad_norm": 0.18478704988956451,
      "learning_rate": 3.370740387928966e-05,
      "loss": 0.0573,
      "mean_token_accuracy": 0.9840769201517106,
      "num_tokens": 36078006.0,
      "step": 200
    },
    {
      "epoch": 0.5828002842928216,
      "grad_norm": 0.1627274453639984,
      "learning_rate": 3.266860597263726e-05,
      "loss": 0.0378,
      "mean_token_accuracy": 0.9881012260913848,
      "num_tokens": 36982125.0,
      "step": 205
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.16685813665390015,
      "learning_rate": 3.16354634374413e-05,
      "loss": 0.0404,
      "mean_token_accuracy": 0.9869986087083816,
      "num_tokens": 37867648.0,
      "step": 210
    },
    {
      "epoch": 0.6112295664534471,
      "grad_norm": 0.2053881734609604,
      "learning_rate": 3.061052860121533e-05,
      "loss": 0.0325,
      "mean_token_accuracy": 0.9910155087709427,
      "num_tokens": 38767603.0,
      "step": 215
    },
    {
      "epoch": 0.6254442075337597,
      "grad_norm": 0.131435364484787,
      "learning_rate": 2.959633351475869e-05,
      "loss": 0.0353,
      "mean_token_accuracy": 0.9893195986747741,
      "num_tokens": 39671113.0,
      "step": 220
    },
    {
      "epoch": 0.6396588486140725,
      "grad_norm": 0.1416647732257843,
      "learning_rate": 2.8595383696850344e-05,
      "loss": 0.0443,
      "mean_token_accuracy": 0.986781644821167,
      "num_tokens": 40585814.0,
      "step": 225
    },
    {
      "epoch": 0.6538734896943852,
      "grad_norm": 0.14536447823047638,
      "learning_rate": 2.7610151944488653e-05,
      "loss": 0.0417,
      "mean_token_accuracy": 0.988651305437088,
      "num_tokens": 41486207.0,
      "step": 230
    },
    {
      "epoch": 0.668088130774698,
      "grad_norm": 0.17438140511512756,
      "learning_rate": 2.6643072223968805e-05,
      "loss": 0.0428,
      "mean_token_accuracy": 0.9874769479036332,
      "num_tokens": 42378742.0,
      "step": 235
    },
    {
      "epoch": 0.6823027718550106,
      "grad_norm": 0.14107723534107208,
      "learning_rate": 2.5696533657889457e-05,
      "loss": 0.0358,
      "mean_token_accuracy": 0.9906654745340348,
      "num_tokens": 43278882.0,
      "step": 240
    },
    {
      "epoch": 0.6965174129353234,
      "grad_norm": 0.2553578019142151,
      "learning_rate": 2.4772874622943578e-05,
      "loss": 0.0453,
      "mean_token_accuracy": 0.9868824750185012,
      "num_tokens": 44155312.0,
      "step": 245
    },
    {
      "epoch": 0.7107320540156361,
      "grad_norm": 0.11934564262628555,
      "learning_rate": 2.3874376973074588e-05,
      "loss": 0.0444,
      "mean_token_accuracy": 0.9873462617397308,
      "num_tokens": 45063924.0,
      "step": 250
    },
    {
      "epoch": 0.7249466950959488,
      "grad_norm": 0.19104401767253876,
      "learning_rate": 2.3003260402269002e-05,
      "loss": 0.0427,
      "mean_token_accuracy": 0.9868784725666047,
      "num_tokens": 45942929.0,
      "step": 255
    }
  ],
  "logging_steps": 5,
  "max_steps": 351,
  "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": 2.7638481726514135e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}