{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.38888888888889,
  "eval_steps": 500,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17,
      "learning_rate": 2.4999999999999998e-05,
      "loss": 1.7264,
      "step": 3
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 1.9502,
      "step": 6
    },
    {
      "epoch": 1.11,
      "learning_rate": 7.5e-05,
      "loss": 1.8229,
      "step": 9
    },
    {
      "epoch": 1.28,
      "learning_rate": 9.999999999999999e-05,
      "loss": 1.4868,
      "step": 12
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.000125,
      "loss": 1.6675,
      "step": 15
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00015,
      "loss": 1.2277,
      "step": 18
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.000175,
      "loss": 1.4422,
      "step": 21
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.00019999999999999998,
      "loss": 1.3051,
      "step": 24
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.000225,
      "loss": 1.0676,
      "step": 27
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.00025,
      "loss": 1.1766,
      "step": 30
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.00027499999999999996,
      "loss": 0.9316,
      "step": 33
    },
    {
      "epoch": 5.06,
      "learning_rate": 0.0003,
      "loss": 0.6064,
      "step": 36
    },
    {
      "epoch": 5.22,
      "learning_rate": 0.00029722222222222216,
      "loss": 0.5883,
      "step": 39
    },
    {
      "epoch": 5.39,
      "learning_rate": 0.00029444444444444445,
      "loss": 0.6243,
      "step": 42
    },
    {
      "epoch": 6.17,
      "learning_rate": 0.00029166666666666664,
      "loss": 0.5,
      "step": 45
    },
    {
      "epoch": 6.33,
      "learning_rate": 0.0002888888888888888,
      "loss": 0.4061,
      "step": 48
    },
    {
      "epoch": 7.11,
      "learning_rate": 0.0002861111111111111,
      "loss": 0.3036,
      "step": 51
    },
    {
      "epoch": 7.28,
      "learning_rate": 0.0002833333333333333,
      "loss": 0.3437,
      "step": 54
    },
    {
      "epoch": 8.06,
      "learning_rate": 0.00028055555555555554,
      "loss": 0.2798,
      "step": 57
    },
    {
      "epoch": 8.22,
      "learning_rate": 0.0002777777777777778,
      "loss": 0.1906,
      "step": 60
    },
    {
      "epoch": 8.39,
      "learning_rate": 0.00027499999999999996,
      "loss": 0.2051,
      "step": 63
    },
    {
      "epoch": 9.17,
      "learning_rate": 0.0002722222222222222,
      "loss": 0.1486,
      "step": 66
    },
    {
      "epoch": 9.33,
      "learning_rate": 0.00026944444444444444,
      "loss": 0.1745,
      "step": 69
    },
    {
      "epoch": 10.11,
      "learning_rate": 0.0002666666666666666,
      "loss": 0.1235,
      "step": 72
    },
    {
      "epoch": 10.28,
      "learning_rate": 0.00026388888888888886,
      "loss": 0.1066,
      "step": 75
    },
    {
      "epoch": 11.06,
      "learning_rate": 0.0002611111111111111,
      "loss": 0.0659,
      "step": 78
    },
    {
      "epoch": 11.22,
      "learning_rate": 0.00025833333333333334,
      "loss": 0.0865,
      "step": 81
    },
    {
      "epoch": 11.39,
      "learning_rate": 0.00025555555555555553,
      "loss": 0.0582,
      "step": 84
    },
    {
      "epoch": 12.17,
      "learning_rate": 0.00025277777777777777,
      "loss": 0.0557,
      "step": 87
    },
    {
      "epoch": 12.33,
      "learning_rate": 0.00025,
      "loss": 0.0528,
      "step": 90
    },
    {
      "epoch": 13.11,
      "learning_rate": 0.0002472222222222222,
      "loss": 0.0384,
      "step": 93
    },
    {
      "epoch": 13.28,
      "learning_rate": 0.00024444444444444443,
      "loss": 0.0341,
      "step": 96
    },
    {
      "epoch": 14.06,
      "learning_rate": 0.00024166666666666664,
      "loss": 0.0294,
      "step": 99
    },
    {
      "epoch": 14.22,
      "learning_rate": 0.00023888888888888885,
      "loss": 0.0193,
      "step": 102
    },
    {
      "epoch": 14.39,
      "learning_rate": 0.00023611111111111112,
      "loss": 0.0254,
      "step": 105
    },
    {
      "epoch": 15.17,
      "learning_rate": 0.0002333333333333333,
      "loss": 0.0192,
      "step": 108
    },
    {
      "epoch": 15.33,
      "learning_rate": 0.00023055555555555552,
      "loss": 0.0149,
      "step": 111
    },
    {
      "epoch": 16.11,
      "learning_rate": 0.00022777777777777778,
      "loss": 0.0194,
      "step": 114
    },
    {
      "epoch": 16.28,
      "learning_rate": 0.000225,
      "loss": 0.0177,
      "step": 117
    },
    {
      "epoch": 17.06,
      "learning_rate": 0.00022222222222222218,
      "loss": 0.0144,
      "step": 120
    },
    {
      "epoch": 17.22,
      "learning_rate": 0.00021944444444444444,
      "loss": 0.013,
      "step": 123
    },
    {
      "epoch": 17.39,
      "learning_rate": 0.00021666666666666666,
      "loss": 0.0165,
      "step": 126
    },
    {
      "epoch": 18.17,
      "learning_rate": 0.00021388888888888884,
      "loss": 0.012,
      "step": 129
    },
    {
      "epoch": 18.33,
      "learning_rate": 0.0002111111111111111,
      "loss": 0.0137,
      "step": 132
    },
    {
      "epoch": 19.11,
      "learning_rate": 0.00020833333333333332,
      "loss": 0.0083,
      "step": 135
    },
    {
      "epoch": 19.28,
      "learning_rate": 0.00020555555555555556,
      "loss": 0.0144,
      "step": 138
    }
  ],
  "logging_steps": 3,
  "max_steps": 360,
  "num_train_epochs": 20,
  "save_steps": 500,
  "total_flos": 1.13811835060224e+16,
  "trial_name": null,
  "trial_params": null
}