{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004,
      "grad_norm": 133.0,
      "learning_rate": 8.000000000000001e-07,
      "loss": 14.6589,
      "step": 10
    },
    {
      "epoch": 0.008,
      "grad_norm": 105.0,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 14.6939,
      "step": 20
    },
    {
      "epoch": 0.012,
      "grad_norm": 147.0,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 14.6547,
      "step": 30
    },
    {
      "epoch": 0.016,
      "grad_norm": 71.0,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 14.3371,
      "step": 40
    },
    {
      "epoch": 0.02,
      "grad_norm": 50.25,
      "learning_rate": 4.000000000000001e-06,
      "loss": 14.3937,
      "step": 50
    },
    {
      "epoch": 0.024,
      "grad_norm": 48.0,
      "learning_rate": 4.800000000000001e-06,
      "loss": 14.1942,
      "step": 60
    },
    {
      "epoch": 0.028,
      "grad_norm": 53.0,
      "learning_rate": 5.600000000000001e-06,
      "loss": 14.1931,
      "step": 70
    },
    {
      "epoch": 0.032,
      "grad_norm": 32.25,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 13.6957,
      "step": 80
    },
    {
      "epoch": 0.036,
      "grad_norm": 49.5,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 13.77,
      "step": 90
    },
    {
      "epoch": 0.04,
      "grad_norm": 49.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 13.6821,
      "step": 100
    },
    {
      "epoch": 0.044,
      "grad_norm": 42.25,
      "learning_rate": 8.8e-06,
      "loss": 13.6035,
      "step": 110
    },
    {
      "epoch": 0.048,
      "grad_norm": 55.5,
      "learning_rate": 9.600000000000001e-06,
      "loss": 13.8774,
      "step": 120
    },
    {
      "epoch": 0.052,
      "grad_norm": 62.75,
      "learning_rate": 1.04e-05,
      "loss": 13.6259,
      "step": 130
    },
    {
      "epoch": 0.056,
      "grad_norm": 55.0,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 13.4089,
      "step": 140
    },
    {
      "epoch": 0.06,
      "grad_norm": 65.5,
      "learning_rate": 1.2e-05,
      "loss": 13.6572,
      "step": 150
    },
    {
      "epoch": 0.064,
      "grad_norm": 68.0,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 13.5695,
      "step": 160
    },
    {
      "epoch": 0.068,
      "grad_norm": 56.0,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 13.5,
      "step": 170
    },
    {
      "epoch": 0.072,
      "grad_norm": 72.0,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 13.5601,
      "step": 180
    },
    {
      "epoch": 0.076,
      "grad_norm": 87.0,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 14.2029,
      "step": 190
    },
    {
      "epoch": 0.08,
      "grad_norm": 83.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 14.2416,
      "step": 200
    },
    {
      "epoch": 0.084,
      "grad_norm": 81.5,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 13.8197,
      "step": 210
    },
    {
      "epoch": 0.088,
      "grad_norm": 75.5,
      "learning_rate": 1.76e-05,
      "loss": 14.1598,
      "step": 220
    },
    {
      "epoch": 0.092,
      "grad_norm": 89.5,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 14.1819,
      "step": 230
    },
    {
      "epoch": 0.096,
      "grad_norm": 76.5,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 13.9713,
      "step": 240
    },
    {
      "epoch": 0.1,
      "grad_norm": 87.0,
      "learning_rate": 2e-05,
      "loss": 14.3763,
      "step": 250
    },
    {
      "epoch": 0.104,
      "grad_norm": 79.0,
      "learning_rate": 1.9999025240093045e-05,
      "loss": 14.4492,
      "step": 260
    },
    {
      "epoch": 0.108,
      "grad_norm": 84.5,
      "learning_rate": 1.9996101150403543e-05,
      "loss": 14.2794,
      "step": 270
    },
    {
      "epoch": 0.112,
      "grad_norm": 84.0,
      "learning_rate": 1.9991228300988586e-05,
      "loss": 14.0471,
      "step": 280
    },
    {
      "epoch": 0.116,
      "grad_norm": 75.0,
      "learning_rate": 1.9984407641819812e-05,
      "loss": 14.3031,
      "step": 290
    },
    {
      "epoch": 0.12,
      "grad_norm": 71.5,
      "learning_rate": 1.9975640502598243e-05,
      "loss": 13.8098,
      "step": 300
    },
    {
      "epoch": 0.124,
      "grad_norm": 70.5,
      "learning_rate": 1.9964928592495046e-05,
      "loss": 14.075,
      "step": 310
    },
    {
      "epoch": 0.128,
      "grad_norm": 63.0,
      "learning_rate": 1.9952273999818312e-05,
      "loss": 14.2647,
      "step": 320
    },
    {
      "epoch": 0.132,
      "grad_norm": 85.0,
      "learning_rate": 1.9937679191605964e-05,
      "loss": 13.6276,
      "step": 330
    },
    {
      "epoch": 0.136,
      "grad_norm": 47.25,
      "learning_rate": 1.9921147013144782e-05,
      "loss": 13.5483,
      "step": 340
    },
    {
      "epoch": 0.14,
      "grad_norm": 84.5,
      "learning_rate": 1.9902680687415704e-05,
      "loss": 13.8993,
      "step": 350
    },
    {
      "epoch": 0.144,
      "grad_norm": 77.0,
      "learning_rate": 1.988228381446553e-05,
      "loss": 13.4859,
      "step": 360
    },
    {
      "epoch": 0.148,
      "grad_norm": 71.5,
      "learning_rate": 1.985996037070505e-05,
      "loss": 13.8062,
      "step": 370
    },
    {
      "epoch": 0.152,
      "grad_norm": 69.0,
      "learning_rate": 1.983571470813386e-05,
      "loss": 13.5252,
      "step": 380
    },
    {
      "epoch": 0.156,
      "grad_norm": 51.5,
      "learning_rate": 1.9809551553491918e-05,
      "loss": 13.3325,
      "step": 390
    },
    {
      "epoch": 0.16,
      "grad_norm": 54.75,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 13.4057,
      "step": 400
    },
    {
      "epoch": 0.164,
      "grad_norm": 54.25,
      "learning_rate": 1.9751493543055634e-05,
      "loss": 13.5621,
      "step": 410
    },
    {
      "epoch": 0.168,
      "grad_norm": 57.75,
      "learning_rate": 1.9719610005785466e-05,
      "loss": 13.4838,
      "step": 420
    },
    {
      "epoch": 0.172,
      "grad_norm": 67.0,
      "learning_rate": 1.9685831611286312e-05,
      "loss": 13.6975,
      "step": 430
    },
    {
      "epoch": 0.176,
      "grad_norm": 63.5,
      "learning_rate": 1.9650164944723116e-05,
      "loss": 13.6201,
      "step": 440
    },
    {
      "epoch": 0.18,
      "grad_norm": 57.5,
      "learning_rate": 1.961261695938319e-05,
      "loss": 13.2647,
      "step": 450
    },
    {
      "epoch": 0.184,
      "grad_norm": 57.75,
      "learning_rate": 1.9573194975320672e-05,
      "loss": 13.1013,
      "step": 460
    },
    {
      "epoch": 0.188,
      "grad_norm": 50.75,
      "learning_rate": 1.9531906677929472e-05,
      "loss": 13.357,
      "step": 470
    },
    {
      "epoch": 0.192,
      "grad_norm": 66.5,
      "learning_rate": 1.9488760116444966e-05,
      "loss": 13.4903,
      "step": 480
    },
    {
      "epoch": 0.196,
      "grad_norm": 57.0,
      "learning_rate": 1.944376370237481e-05,
      "loss": 13.4989,
      "step": 490
    },
    {
      "epoch": 0.2,
      "grad_norm": 35.0,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 13.265,
      "step": 500
    },
    {
      "epoch": 0.204,
      "grad_norm": 48.0,
      "learning_rate": 1.9348256763960146e-05,
      "loss": 13.3747,
      "step": 510
    },
    {
      "epoch": 0.208,
      "grad_norm": 65.5,
      "learning_rate": 1.9297764858882516e-05,
      "loss": 12.9383,
      "step": 520
    },
    {
      "epoch": 0.212,
      "grad_norm": 70.0,
      "learning_rate": 1.9245460336123136e-05,
      "loss": 13.3839,
      "step": 530
    },
    {
      "epoch": 0.216,
      "grad_norm": 53.5,
      "learning_rate": 1.9191353392552346e-05,
      "loss": 13.0719,
      "step": 540
    },
    {
      "epoch": 0.22,
      "grad_norm": 60.75,
      "learning_rate": 1.913545457642601e-05,
      "loss": 13.4937,
      "step": 550
    },
    {
      "epoch": 0.224,
      "grad_norm": 62.25,
      "learning_rate": 1.907777478532909e-05,
      "loss": 13.4174,
      "step": 560
    },
    {
      "epoch": 0.228,
      "grad_norm": 40.0,
      "learning_rate": 1.901832526405114e-05,
      "loss": 12.7041,
      "step": 570
    },
    {
      "epoch": 0.232,
      "grad_norm": 44.75,
      "learning_rate": 1.895711760239413e-05,
      "loss": 12.8224,
      "step": 580
    },
    {
      "epoch": 0.236,
      "grad_norm": 58.75,
      "learning_rate": 1.889416373291298e-05,
      "loss": 13.2145,
      "step": 590
    },
    {
      "epoch": 0.24,
      "grad_norm": 63.75,
      "learning_rate": 1.8829475928589272e-05,
      "loss": 12.9917,
      "step": 600
    },
    {
      "epoch": 0.244,
      "grad_norm": 55.75,
      "learning_rate": 1.8763066800438638e-05,
      "loss": 13.0001,
      "step": 610
    },
    {
      "epoch": 0.248,
      "grad_norm": 64.0,
      "learning_rate": 1.869494929505219e-05,
      "loss": 12.8902,
      "step": 620
    },
    {
      "epoch": 0.252,
      "grad_norm": 56.25,
      "learning_rate": 1.8625136692072577e-05,
      "loss": 12.8643,
      "step": 630
    },
    {
      "epoch": 0.256,
      "grad_norm": 50.75,
      "learning_rate": 1.855364260160507e-05,
      "loss": 13.1711,
      "step": 640
    },
    {
      "epoch": 0.26,
      "grad_norm": 44.0,
      "learning_rate": 1.848048096156426e-05,
      "loss": 12.4998,
      "step": 650
    },
    {
      "epoch": 0.264,
      "grad_norm": 49.25,
      "learning_rate": 1.8405666034956842e-05,
      "loss": 13.0156,
      "step": 660
    },
    {
      "epoch": 0.268,
      "grad_norm": 50.5,
      "learning_rate": 1.8329212407100996e-05,
      "loss": 13.0544,
      "step": 670
    },
    {
      "epoch": 0.272,
      "grad_norm": 46.75,
      "learning_rate": 1.8251134982782952e-05,
      "loss": 12.6195,
      "step": 680
    },
    {
      "epoch": 0.276,
      "grad_norm": 44.0,
      "learning_rate": 1.8171448983351284e-05,
      "loss": 12.7227,
      "step": 690
    },
    {
      "epoch": 0.28,
      "grad_norm": 46.25,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 12.8001,
      "step": 700
    },
    {
      "epoch": 0.284,
      "grad_norm": 35.25,
      "learning_rate": 1.8007313709487334e-05,
      "loss": 12.5228,
      "step": 710
    },
    {
      "epoch": 0.288,
      "grad_norm": 47.75,
      "learning_rate": 1.792289643355191e-05,
      "loss": 12.1604,
      "step": 720
    },
    {
      "epoch": 0.292,
      "grad_norm": 42.5,
      "learning_rate": 1.78369345732584e-05,
      "loss": 12.9349,
      "step": 730
    },
    {
      "epoch": 0.296,
      "grad_norm": 43.0,
      "learning_rate": 1.7749444887041797e-05,
      "loss": 12.7243,
      "step": 740
    },
    {
      "epoch": 0.3,
      "grad_norm": 44.25,
      "learning_rate": 1.766044443118978e-05,
      "loss": 12.5963,
      "step": 750
    },
    {
      "epoch": 0.304,
      "grad_norm": 39.75,
      "learning_rate": 1.7569950556517566e-05,
      "loss": 12.615,
      "step": 760
    },
    {
      "epoch": 0.308,
      "grad_norm": 48.25,
      "learning_rate": 1.747798090498532e-05,
      "loss": 12.4486,
      "step": 770
    },
    {
      "epoch": 0.312,
      "grad_norm": 45.5,
      "learning_rate": 1.7384553406258842e-05,
      "loss": 12.5418,
      "step": 780
    },
    {
      "epoch": 0.316,
      "grad_norm": 47.0,
      "learning_rate": 1.7289686274214116e-05,
      "loss": 12.7136,
      "step": 790
    },
    {
      "epoch": 0.32,
      "grad_norm": 47.5,
      "learning_rate": 1.7193398003386514e-05,
      "loss": 12.6104,
      "step": 800
    },
    {
      "epoch": 0.324,
      "grad_norm": 52.75,
      "learning_rate": 1.709570736536521e-05,
      "loss": 12.5984,
      "step": 810
    },
    {
      "epoch": 0.328,
      "grad_norm": 52.0,
      "learning_rate": 1.6996633405133656e-05,
      "loss": 12.2448,
      "step": 820
    },
    {
      "epoch": 0.332,
      "grad_norm": 49.25,
      "learning_rate": 1.68961954373567e-05,
      "loss": 12.0836,
      "step": 830
    },
    {
      "epoch": 0.336,
      "grad_norm": 47.5,
      "learning_rate": 1.6794413042615168e-05,
      "loss": 12.2394,
      "step": 840
    },
    {
      "epoch": 0.34,
      "grad_norm": 47.25,
      "learning_rate": 1.6691306063588583e-05,
      "loss": 12.2065,
      "step": 850
    },
    {
      "epoch": 0.344,
      "grad_norm": 44.0,
      "learning_rate": 1.6586894601186804e-05,
      "loss": 12.4923,
      "step": 860
    },
    {
      "epoch": 0.348,
      "grad_norm": 42.5,
      "learning_rate": 1.6481199010631312e-05,
      "loss": 12.3164,
      "step": 870
    },
    {
      "epoch": 0.352,
      "grad_norm": 38.0,
      "learning_rate": 1.63742398974869e-05,
      "loss": 12.6115,
      "step": 880
    },
    {
      "epoch": 0.356,
      "grad_norm": 42.0,
      "learning_rate": 1.6266038113644605e-05,
      "loss": 12.3281,
      "step": 890
    },
    {
      "epoch": 0.36,
      "grad_norm": 32.75,
      "learning_rate": 1.6156614753256583e-05,
      "loss": 12.1486,
      "step": 900
    },
    {
      "epoch": 0.364,
      "grad_norm": 43.75,
      "learning_rate": 1.6045991148623752e-05,
      "loss": 12.3493,
      "step": 910
    },
    {
      "epoch": 0.368,
      "grad_norm": 47.0,
      "learning_rate": 1.5934188866037017e-05,
      "loss": 12.3741,
      "step": 920
    },
    {
      "epoch": 0.372,
      "grad_norm": 39.5,
      "learning_rate": 1.5821229701572897e-05,
      "loss": 12.2705,
      "step": 930
    },
    {
      "epoch": 0.376,
      "grad_norm": 29.625,
      "learning_rate": 1.570713567684432e-05,
      "loss": 12.4079,
      "step": 940
    },
    {
      "epoch": 0.38,
      "grad_norm": 31.75,
      "learning_rate": 1.5591929034707468e-05,
      "loss": 12.0353,
      "step": 950
    },
    {
      "epoch": 0.384,
      "grad_norm": 42.75,
      "learning_rate": 1.5475632234925505e-05,
      "loss": 12.2648,
      "step": 960
    },
    {
      "epoch": 0.388,
      "grad_norm": 35.5,
      "learning_rate": 1.5358267949789968e-05,
      "loss": 12.0796,
      "step": 970
    },
    {
      "epoch": 0.392,
      "grad_norm": 25.625,
      "learning_rate": 1.5239859059700794e-05,
      "loss": 12.5451,
      "step": 980
    },
    {
      "epoch": 0.396,
      "grad_norm": 33.75,
      "learning_rate": 1.5120428648705716e-05,
      "loss": 12.1473,
      "step": 990
    },
    {
      "epoch": 0.4,
      "grad_norm": 36.5,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 12.2316,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "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": 1.91328310788096e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}