{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9969666329625886,
  "eval_steps": 500,
  "global_step": 741,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04044489383215369,
      "grad_norm": 0.32977694272994995,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.0598,
      "step": 10
    },
    {
      "epoch": 0.08088978766430738,
      "grad_norm": 0.37004101276397705,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.9336,
      "step": 20
    },
    {
      "epoch": 0.12133468149646107,
      "grad_norm": 0.4031585156917572,
      "learning_rate": 4e-05,
      "loss": 0.8984,
      "step": 30
    },
    {
      "epoch": 0.16177957532861476,
      "grad_norm": 1.509679913520813,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.8535,
      "step": 40
    },
    {
      "epoch": 0.20222446916076844,
      "grad_norm": 0.49513012170791626,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.8269,
      "step": 50
    },
    {
      "epoch": 0.24266936299292213,
      "grad_norm": 0.6064131855964661,
      "learning_rate": 8e-05,
      "loss": 0.8761,
      "step": 60
    },
    {
      "epoch": 0.28311425682507585,
      "grad_norm": 0.5522051453590393,
      "learning_rate": 9.333333333333334e-05,
      "loss": 0.8263,
      "step": 70
    },
    {
      "epoch": 0.3235591506572295,
      "grad_norm": 0.6795193552970886,
      "learning_rate": 9.998609371351944e-05,
      "loss": 0.8209,
      "step": 80
    },
    {
      "epoch": 0.3640040444893832,
      "grad_norm": 1.0687181949615479,
      "learning_rate": 9.9874889829725e-05,
      "loss": 0.8256,
      "step": 90
    },
    {
      "epoch": 0.4044489383215369,
      "grad_norm": 0.44715842604637146,
      "learning_rate": 9.965272945701839e-05,
      "loss": 0.8317,
      "step": 100
    },
    {
      "epoch": 0.4448938321536906,
      "grad_norm": 0.5097022652626038,
      "learning_rate": 9.932010683478573e-05,
      "loss": 0.7896,
      "step": 110
    },
    {
      "epoch": 0.48533872598584427,
      "grad_norm": 0.3602050840854645,
      "learning_rate": 9.887776194738432e-05,
      "loss": 0.7551,
      "step": 120
    },
    {
      "epoch": 0.5257836198179979,
      "grad_norm": 0.5977407693862915,
      "learning_rate": 9.832667887790208e-05,
      "loss": 0.8371,
      "step": 130
    },
    {
      "epoch": 0.5662285136501517,
      "grad_norm": 0.376720130443573,
      "learning_rate": 9.766808361887147e-05,
      "loss": 0.6978,
      "step": 140
    },
    {
      "epoch": 0.6066734074823054,
      "grad_norm": 0.6886475086212158,
      "learning_rate": 9.69034413448083e-05,
      "loss": 0.7482,
      "step": 150
    },
    {
      "epoch": 0.647118301314459,
      "grad_norm": 0.6275140047073364,
      "learning_rate": 9.603445315264317e-05,
      "loss": 0.7765,
      "step": 160
    },
    {
      "epoch": 0.6875631951466128,
      "grad_norm": 0.795728325843811,
      "learning_rate": 9.506305227729723e-05,
      "loss": 0.7824,
      "step": 170
    },
    {
      "epoch": 0.7280080889787665,
      "grad_norm": 0.3607877194881439,
      "learning_rate": 9.399139979082148e-05,
      "loss": 0.865,
      "step": 180
    },
    {
      "epoch": 0.7684529828109201,
      "grad_norm": 0.5607595443725586,
      "learning_rate": 9.282187979466729e-05,
      "loss": 0.7783,
      "step": 190
    },
    {
      "epoch": 0.8088978766430738,
      "grad_norm": 0.7133780121803284,
      "learning_rate": 9.155709411578468e-05,
      "loss": 0.766,
      "step": 200
    },
    {
      "epoch": 0.8493427704752275,
      "grad_norm": 0.3629770576953888,
      "learning_rate": 9.019985651834703e-05,
      "loss": 0.7815,
      "step": 210
    },
    {
      "epoch": 0.8897876643073812,
      "grad_norm": 0.656274676322937,
      "learning_rate": 8.875318644398008e-05,
      "loss": 0.7829,
      "step": 220
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 0.4777781367301941,
      "learning_rate": 8.722030229442095e-05,
      "loss": 0.7668,
      "step": 230
    },
    {
      "epoch": 0.9706774519716885,
      "grad_norm": 0.46228083968162537,
      "learning_rate": 8.560461427155128e-05,
      "loss": 0.7282,
      "step": 240
    },
    {
      "epoch": 1.0111223458038423,
      "grad_norm": 0.38738882541656494,
      "learning_rate": 8.390971679073332e-05,
      "loss": 0.718,
      "step": 250
    },
    {
      "epoch": 1.0515672396359959,
      "grad_norm": 0.3507082760334015,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.6764,
      "step": 260
    },
    {
      "epoch": 1.0920121334681496,
      "grad_norm": 0.5163873434066772,
      "learning_rate": 8.029754381317741e-05,
      "loss": 0.7534,
      "step": 270
    },
    {
      "epoch": 1.1324570273003034,
      "grad_norm": 0.41655170917510986,
      "learning_rate": 7.838830430473539e-05,
      "loss": 0.7141,
      "step": 280
    },
    {
      "epoch": 1.172901921132457,
      "grad_norm": 0.5573180913925171,
      "learning_rate": 7.641590943730258e-05,
      "loss": 0.698,
      "step": 290
    },
    {
      "epoch": 1.2133468149646107,
      "grad_norm": 0.4728916585445404,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.7408,
      "step": 300
    },
    {
      "epoch": 1.2537917087967645,
      "grad_norm": 0.5964640974998474,
      "learning_rate": 7.22993362842538e-05,
      "loss": 0.7214,
      "step": 310
    },
    {
      "epoch": 1.294236602628918,
      "grad_norm": 0.4228028655052185,
      "learning_rate": 7.016431612419907e-05,
      "loss": 0.7472,
      "step": 320
    },
    {
      "epoch": 1.3346814964610718,
      "grad_norm": 0.4832104444503784,
      "learning_rate": 6.79844364822268e-05,
      "loss": 0.6434,
      "step": 330
    },
    {
      "epoch": 1.3751263902932256,
      "grad_norm": 0.6881019473075867,
      "learning_rate": 6.576454692877513e-05,
      "loss": 0.7244,
      "step": 340
    },
    {
      "epoch": 1.4155712841253791,
      "grad_norm": 0.4529273509979248,
      "learning_rate": 6.35095860441891e-05,
      "loss": 0.7019,
      "step": 350
    },
    {
      "epoch": 1.456016177957533,
      "grad_norm": 0.40597546100616455,
      "learning_rate": 6.122457043187862e-05,
      "loss": 0.6734,
      "step": 360
    },
    {
      "epoch": 1.4964610717896867,
      "grad_norm": 1.0302621126174927,
      "learning_rate": 5.891458355789879e-05,
      "loss": 0.6775,
      "step": 370
    },
    {
      "epoch": 1.5369059656218402,
      "grad_norm": 0.7270640134811401,
      "learning_rate": 5.658476444178118e-05,
      "loss": 0.6988,
      "step": 380
    },
    {
      "epoch": 1.5773508594539938,
      "grad_norm": 0.9417754411697388,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.7473,
      "step": 390
    },
    {
      "epoch": 1.6177957532861478,
      "grad_norm": 0.519805908203125,
      "learning_rate": 5.1886394633935865e-05,
      "loss": 0.6724,
      "step": 400
    },
    {
      "epoch": 1.6582406471183013,
      "grad_norm": 0.38718143105506897,
      "learning_rate": 4.952829638870516e-05,
      "loss": 0.6676,
      "step": 410
    },
    {
      "epoch": 1.6986855409504549,
      "grad_norm": 0.5094408392906189,
      "learning_rate": 4.717124754081038e-05,
      "loss": 0.6828,
      "step": 420
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.8842711448669434,
      "learning_rate": 4.4820491808388036e-05,
      "loss": 0.7012,
      "step": 430
    },
    {
      "epoch": 1.7795753286147624,
      "grad_norm": 0.44060903787612915,
      "learning_rate": 4.2481258909303165e-05,
      "loss": 0.7331,
      "step": 440
    },
    {
      "epoch": 1.820020222446916,
      "grad_norm": 0.8252304196357727,
      "learning_rate": 4.0158752926614736e-05,
      "loss": 0.651,
      "step": 450
    },
    {
      "epoch": 1.8604651162790697,
      "grad_norm": 0.779067873954773,
      "learning_rate": 3.7858140731070646e-05,
      "loss": 0.6252,
      "step": 460
    },
    {
      "epoch": 1.9009100101112235,
      "grad_norm": 0.8989632725715637,
      "learning_rate": 3.5584540486388904e-05,
      "loss": 0.6731,
      "step": 470
    },
    {
      "epoch": 1.941354903943377,
      "grad_norm": 0.8114097118377686,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.688,
      "step": 480
    },
    {
      "epoch": 1.9817997977755308,
      "grad_norm": 0.8452021479606628,
      "learning_rate": 3.113853678486151e-05,
      "loss": 0.6877,
      "step": 490
    },
    {
      "epoch": 2.0222446916076846,
      "grad_norm": 0.32683417201042175,
      "learning_rate": 2.89760243365393e-05,
      "loss": 0.7022,
      "step": 500
    },
    {
      "epoch": 2.0222446916076846,
      "eval_loss": 0.7777388095855713,
      "eval_runtime": 14.8948,
      "eval_samples_per_second": 14.77,
      "eval_steps_per_second": 14.77,
      "step": 500
    },
    {
      "epoch": 2.062689585439838,
      "grad_norm": 0.6976883411407471,
      "learning_rate": 2.6860283851635065e-05,
      "loss": 0.6789,
      "step": 510
    },
    {
      "epoch": 2.1031344792719917,
      "grad_norm": 0.5700914263725281,
      "learning_rate": 2.4796022210433767e-05,
      "loss": 0.6045,
      "step": 520
    },
    {
      "epoch": 2.1435793731041457,
      "grad_norm": 0.7176660895347595,
      "learning_rate": 2.2787831768421046e-05,
      "loss": 0.5851,
      "step": 530
    },
    {
      "epoch": 2.1840242669362993,
      "grad_norm": 0.42338210344314575,
      "learning_rate": 2.0840180139686334e-05,
      "loss": 0.5445,
      "step": 540
    },
    {
      "epoch": 2.224469160768453,
      "grad_norm": 0.5574066638946533,
      "learning_rate": 1.895740025783782e-05,
      "loss": 0.6711,
      "step": 550
    },
    {
      "epoch": 2.264914054600607,
      "grad_norm": 0.5283611416816711,
      "learning_rate": 1.7143680736540574e-05,
      "loss": 0.5776,
      "step": 560
    },
    {
      "epoch": 2.3053589484327603,
      "grad_norm": 0.8224833011627197,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.6412,
      "step": 570
    },
    {
      "epoch": 2.345803842264914,
      "grad_norm": 0.6981547474861145,
      "learning_rate": 1.373940006198014e-05,
      "loss": 0.5975,
      "step": 580
    },
    {
      "epoch": 2.386248736097068,
      "grad_norm": 0.7778781056404114,
      "learning_rate": 1.2156412399750422e-05,
      "loss": 0.6177,
      "step": 590
    },
    {
      "epoch": 2.4266936299292214,
      "grad_norm": 0.6286150813102722,
      "learning_rate": 1.0657615231420493e-05,
      "loss": 0.6231,
      "step": 600
    },
    {
      "epoch": 2.467138523761375,
      "grad_norm": 0.5124749541282654,
      "learning_rate": 9.246342925686885e-06,
      "loss": 0.6518,
      "step": 610
    },
    {
      "epoch": 2.507583417593529,
      "grad_norm": 0.671191394329071,
      "learning_rate": 7.925735134997492e-06,
      "loss": 0.5655,
      "step": 620
    },
    {
      "epoch": 2.5480283114256825,
      "grad_norm": 0.45089051127433777,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.5719,
      "step": 630
    },
    {
      "epoch": 2.588473205257836,
      "grad_norm": 0.8623360395431519,
      "learning_rate": 5.56805666738221e-06,
      "loss": 0.6901,
      "step": 640
    },
    {
      "epoch": 2.62891809908999,
      "grad_norm": 0.522199809551239,
      "learning_rate": 4.536231109305577e-06,
      "loss": 0.6108,
      "step": 650
    },
    {
      "epoch": 2.6693629929221436,
      "grad_norm": 1.2643201351165771,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.6145,
      "step": 660
    },
    {
      "epoch": 2.709807886754297,
      "grad_norm": 0.8499836921691895,
      "learning_rate": 2.7780797309585606e-06,
      "loss": 0.5928,
      "step": 670
    },
    {
      "epoch": 2.750252780586451,
      "grad_norm": 0.713811457157135,
      "learning_rate": 2.0556652637675143e-06,
      "loss": 0.5374,
      "step": 680
    },
    {
      "epoch": 2.7906976744186047,
      "grad_norm": 0.7115636467933655,
      "learning_rate": 1.4399123864811903e-06,
      "loss": 0.5949,
      "step": 690
    },
    {
      "epoch": 2.8311425682507583,
      "grad_norm": 0.6987712979316711,
      "learning_rate": 9.321909623220271e-07,
      "loss": 0.6557,
      "step": 700
    },
    {
      "epoch": 2.8715874620829123,
      "grad_norm": 0.4708057940006256,
      "learning_rate": 5.336305173253231e-07,
      "loss": 0.6258,
      "step": 710
    },
    {
      "epoch": 2.912032355915066,
      "grad_norm": 0.8962985873222351,
      "learning_rate": 2.451177274866989e-07,
      "loss": 0.5874,
      "step": 720
    },
    {
      "epoch": 2.9524772497472194,
      "grad_norm": 0.7313467860221863,
      "learning_rate": 6.729444617717961e-08,
      "loss": 0.6104,
      "step": 730
    },
    {
      "epoch": 2.9929221435793734,
      "grad_norm": 0.69645094871521,
      "learning_rate": 5.562762142974353e-10,
      "loss": 0.5679,
      "step": 740
    },
    {
      "epoch": 2.9969666329625886,
      "step": 741,
      "total_flos": 4.204244398782874e+16,
      "train_loss": 0.7069849928944056,
      "train_runtime": 1363.5787,
      "train_samples_per_second": 4.352,
      "train_steps_per_second": 0.543
    }
  ],
  "logging_steps": 10,
  "max_steps": 741,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.204244398782874e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}