{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9955555555555555,
  "eval_steps": 100,
  "global_step": 562,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 11.767955780029297,
      "learning_rate": 0.00019679715302491104,
      "loss": 33.6554,
      "step": 10
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 9.438668251037598,
      "learning_rate": 0.0001932384341637011,
      "loss": 33.8787,
      "step": 20
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 10.174617767333984,
      "learning_rate": 0.00018967971530249112,
      "loss": 33.8919,
      "step": 30
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 8.84274673461914,
      "learning_rate": 0.00018612099644128114,
      "loss": 33.7011,
      "step": 40
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 10.169342041015625,
      "learning_rate": 0.0001825622775800712,
      "loss": 33.6306,
      "step": 50
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 9.339362144470215,
      "learning_rate": 0.0001790035587188612,
      "loss": 33.5378,
      "step": 60
    },
    {
      "epoch": 0.24888888888888888,
      "grad_norm": 10.399051666259766,
      "learning_rate": 0.00017544483985765125,
      "loss": 33.1223,
      "step": 70
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 8.772202491760254,
      "learning_rate": 0.00017188612099644127,
      "loss": 34.3864,
      "step": 80
    },
    {
      "epoch": 0.32,
      "grad_norm": 9.338233947753906,
      "learning_rate": 0.00016832740213523133,
      "loss": 33.2955,
      "step": 90
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 9.439739227294922,
      "learning_rate": 0.00016476868327402135,
      "loss": 33.229,
      "step": 100
    },
    {
      "epoch": 0.35555555555555557,
      "eval_loss": 2.133469820022583,
      "eval_runtime": 296.1668,
      "eval_samples_per_second": 3.376,
      "eval_steps_per_second": 0.422,
      "step": 100
    },
    {
      "epoch": 0.39111111111111113,
      "grad_norm": 9.046673774719238,
      "learning_rate": 0.0001612099644128114,
      "loss": 33.3667,
      "step": 110
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 8.99227237701416,
      "learning_rate": 0.00015765124555160143,
      "loss": 32.6701,
      "step": 120
    },
    {
      "epoch": 0.4622222222222222,
      "grad_norm": 7.6904144287109375,
      "learning_rate": 0.00015409252669039148,
      "loss": 33.2927,
      "step": 130
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 8.012206077575684,
      "learning_rate": 0.00015053380782918148,
      "loss": 33.2934,
      "step": 140
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 10.931622505187988,
      "learning_rate": 0.00014697508896797153,
      "loss": 33.3676,
      "step": 150
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 7.606035232543945,
      "learning_rate": 0.00014341637010676156,
      "loss": 34.1758,
      "step": 160
    },
    {
      "epoch": 0.6044444444444445,
      "grad_norm": 9.531214714050293,
      "learning_rate": 0.0001398576512455516,
      "loss": 33.0847,
      "step": 170
    },
    {
      "epoch": 0.64,
      "grad_norm": 8.761300086975098,
      "learning_rate": 0.00013629893238434164,
      "loss": 33.5206,
      "step": 180
    },
    {
      "epoch": 0.6755555555555556,
      "grad_norm": 9.155729293823242,
      "learning_rate": 0.0001327402135231317,
      "loss": 33.2403,
      "step": 190
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 9.354476928710938,
      "learning_rate": 0.00012918149466192172,
      "loss": 33.5548,
      "step": 200
    },
    {
      "epoch": 0.7111111111111111,
      "eval_loss": 2.126850128173828,
      "eval_runtime": 296.1679,
      "eval_samples_per_second": 3.376,
      "eval_steps_per_second": 0.422,
      "step": 200
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 8.922224998474121,
      "learning_rate": 0.00012562277580071177,
      "loss": 33.279,
      "step": 210
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 9.973633766174316,
      "learning_rate": 0.00012206405693950178,
      "loss": 33.5481,
      "step": 220
    },
    {
      "epoch": 0.8177777777777778,
      "grad_norm": 8.771803855895996,
      "learning_rate": 0.00011850533807829183,
      "loss": 33.1058,
      "step": 230
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 10.16543960571289,
      "learning_rate": 0.00011494661921708185,
      "loss": 33.3706,
      "step": 240
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 9.286821365356445,
      "learning_rate": 0.0001113879003558719,
      "loss": 33.3456,
      "step": 250
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 9.520956039428711,
      "learning_rate": 0.00010782918149466192,
      "loss": 33.5781,
      "step": 260
    },
    {
      "epoch": 0.96,
      "grad_norm": 10.376456260681152,
      "learning_rate": 0.00010427046263345198,
      "loss": 32.9687,
      "step": 270
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 8.36178207397461,
      "learning_rate": 0.00010071174377224199,
      "loss": 33.7239,
      "step": 280
    },
    {
      "epoch": 1.0284444444444445,
      "grad_norm": 10.113052368164062,
      "learning_rate": 9.715302491103203e-05,
      "loss": 29.9997,
      "step": 290
    },
    {
      "epoch": 1.064,
      "grad_norm": 11.123631477355957,
      "learning_rate": 9.359430604982207e-05,
      "loss": 32.5004,
      "step": 300
    },
    {
      "epoch": 1.064,
      "eval_loss": 2.122236490249634,
      "eval_runtime": 296.127,
      "eval_samples_per_second": 3.377,
      "eval_steps_per_second": 0.422,
      "step": 300
    },
    {
      "epoch": 1.0995555555555556,
      "grad_norm": 9.897551536560059,
      "learning_rate": 9.00355871886121e-05,
      "loss": 32.5046,
      "step": 310
    },
    {
      "epoch": 1.1351111111111112,
      "grad_norm": 9.53073501586914,
      "learning_rate": 8.647686832740213e-05,
      "loss": 32.2727,
      "step": 320
    },
    {
      "epoch": 1.1706666666666667,
      "grad_norm": 10.394311904907227,
      "learning_rate": 8.291814946619217e-05,
      "loss": 32.688,
      "step": 330
    },
    {
      "epoch": 1.2062222222222223,
      "grad_norm": 9.498970031738281,
      "learning_rate": 7.935943060498221e-05,
      "loss": 33.6316,
      "step": 340
    },
    {
      "epoch": 1.2417777777777779,
      "grad_norm": 10.150975227355957,
      "learning_rate": 7.580071174377225e-05,
      "loss": 33.0713,
      "step": 350
    },
    {
      "epoch": 1.2773333333333334,
      "grad_norm": 9.899177551269531,
      "learning_rate": 7.224199288256229e-05,
      "loss": 32.4769,
      "step": 360
    },
    {
      "epoch": 1.3128888888888888,
      "grad_norm": 9.39831829071045,
      "learning_rate": 6.868327402135231e-05,
      "loss": 32.2654,
      "step": 370
    },
    {
      "epoch": 1.3484444444444446,
      "grad_norm": 10.761151313781738,
      "learning_rate": 6.512455516014235e-05,
      "loss": 32.491,
      "step": 380
    },
    {
      "epoch": 1.384,
      "grad_norm": 9.932414054870605,
      "learning_rate": 6.156583629893239e-05,
      "loss": 33.5308,
      "step": 390
    },
    {
      "epoch": 1.4195555555555557,
      "grad_norm": 11.054327011108398,
      "learning_rate": 5.8007117437722425e-05,
      "loss": 31.7061,
      "step": 400
    },
    {
      "epoch": 1.4195555555555557,
      "eval_loss": 2.120673418045044,
      "eval_runtime": 296.1092,
      "eval_samples_per_second": 3.377,
      "eval_steps_per_second": 0.422,
      "step": 400
    },
    {
      "epoch": 1.455111111111111,
      "grad_norm": 10.89476203918457,
      "learning_rate": 5.4448398576512464e-05,
      "loss": 32.485,
      "step": 410
    },
    {
      "epoch": 1.4906666666666666,
      "grad_norm": 9.823376655578613,
      "learning_rate": 5.0889679715302496e-05,
      "loss": 32.9951,
      "step": 420
    },
    {
      "epoch": 1.5262222222222221,
      "grad_norm": 11.316079139709473,
      "learning_rate": 4.733096085409253e-05,
      "loss": 32.3443,
      "step": 430
    },
    {
      "epoch": 1.561777777777778,
      "grad_norm": 11.608524322509766,
      "learning_rate": 4.377224199288256e-05,
      "loss": 32.2948,
      "step": 440
    },
    {
      "epoch": 1.5973333333333333,
      "grad_norm": 11.020298957824707,
      "learning_rate": 4.02135231316726e-05,
      "loss": 32.6702,
      "step": 450
    },
    {
      "epoch": 1.6328888888888888,
      "grad_norm": 9.804555892944336,
      "learning_rate": 3.665480427046263e-05,
      "loss": 31.6452,
      "step": 460
    },
    {
      "epoch": 1.6684444444444444,
      "grad_norm": 11.037073135375977,
      "learning_rate": 3.309608540925267e-05,
      "loss": 32.479,
      "step": 470
    },
    {
      "epoch": 1.704,
      "grad_norm": 9.837021827697754,
      "learning_rate": 2.9537366548042704e-05,
      "loss": 32.72,
      "step": 480
    },
    {
      "epoch": 1.7395555555555555,
      "grad_norm": 11.720721244812012,
      "learning_rate": 2.597864768683274e-05,
      "loss": 32.6789,
      "step": 490
    },
    {
      "epoch": 1.775111111111111,
      "grad_norm": 11.738125801086426,
      "learning_rate": 2.2419928825622775e-05,
      "loss": 33.3128,
      "step": 500
    },
    {
      "epoch": 1.775111111111111,
      "eval_loss": 2.11881947517395,
      "eval_runtime": 296.1216,
      "eval_samples_per_second": 3.377,
      "eval_steps_per_second": 0.422,
      "step": 500
    },
    {
      "epoch": 1.8106666666666666,
      "grad_norm": 11.249613761901855,
      "learning_rate": 1.8861209964412814e-05,
      "loss": 31.9298,
      "step": 510
    },
    {
      "epoch": 1.8462222222222222,
      "grad_norm": 11.530637741088867,
      "learning_rate": 1.530249110320285e-05,
      "loss": 31.8878,
      "step": 520
    },
    {
      "epoch": 1.8817777777777778,
      "grad_norm": 11.147592544555664,
      "learning_rate": 1.1743772241992882e-05,
      "loss": 32.6852,
      "step": 530
    },
    {
      "epoch": 1.9173333333333333,
      "grad_norm": 9.81916332244873,
      "learning_rate": 8.185053380782918e-06,
      "loss": 32.1578,
      "step": 540
    },
    {
      "epoch": 1.952888888888889,
      "grad_norm": 10.557317733764648,
      "learning_rate": 4.626334519572954e-06,
      "loss": 32.2151,
      "step": 550
    },
    {
      "epoch": 1.9884444444444445,
      "grad_norm": 10.493524551391602,
      "learning_rate": 1.0676156583629894e-06,
      "loss": 31.9549,
      "step": 560
    }
  ],
  "logging_steps": 10,
  "max_steps": 562,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.93400073703424e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}