{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.4,
  "eval_steps": 500,
  "global_step": 280,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "learning_rate": 0.0001,
      "loss": 1.638,
      "step": 7
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 1.7376,
      "step": 14
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0003,
      "loss": 1.3745,
      "step": 21
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0004,
      "loss": 1.0169,
      "step": 28
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0005,
      "loss": 0.7142,
      "step": 35
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0006,
      "loss": 0.591,
      "step": 42
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0007,
      "loss": 0.3283,
      "step": 49
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.0008,
      "loss": 0.4281,
      "step": 56
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.0009000000000000001,
      "loss": 0.2162,
      "step": 63
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.001,
      "loss": 0.1895,
      "step": 70
    },
    {
      "epoch": 5.2,
      "learning_rate": 0.000988888888888889,
      "loss": 0.1243,
      "step": 77
    },
    {
      "epoch": 5.4,
      "learning_rate": 0.0009777777777777777,
      "loss": 0.1904,
      "step": 84
    },
    {
      "epoch": 6.2,
      "learning_rate": 0.0009666666666666667,
      "loss": 0.1011,
      "step": 91
    },
    {
      "epoch": 6.4,
      "learning_rate": 0.0009555555555555556,
      "loss": 0.116,
      "step": 98
    },
    {
      "epoch": 7.2,
      "learning_rate": 0.0009444444444444445,
      "loss": 0.1028,
      "step": 105
    },
    {
      "epoch": 7.4,
      "learning_rate": 0.0009333333333333333,
      "loss": 0.0733,
      "step": 112
    },
    {
      "epoch": 8.2,
      "learning_rate": 0.0009238095238095239,
      "loss": 0.1564,
      "step": 119
    },
    {
      "epoch": 8.4,
      "learning_rate": 0.0009126984126984126,
      "loss": 0.0727,
      "step": 126
    },
    {
      "epoch": 9.2,
      "learning_rate": 0.0009015873015873016,
      "loss": 0.1515,
      "step": 133
    },
    {
      "epoch": 9.4,
      "learning_rate": 0.0008904761904761904,
      "loss": 0.0682,
      "step": 140
    },
    {
      "epoch": 10.2,
      "learning_rate": 0.0008793650793650794,
      "loss": 0.0594,
      "step": 147
    },
    {
      "epoch": 10.4,
      "learning_rate": 0.0008682539682539683,
      "loss": 0.137,
      "step": 154
    },
    {
      "epoch": 11.2,
      "learning_rate": 0.0008571428571428571,
      "loss": 0.0514,
      "step": 161
    },
    {
      "epoch": 11.4,
      "learning_rate": 0.0008460317460317461,
      "loss": 0.0494,
      "step": 168
    },
    {
      "epoch": 12.2,
      "learning_rate": 0.000834920634920635,
      "loss": 0.0306,
      "step": 175
    },
    {
      "epoch": 12.4,
      "learning_rate": 0.0008238095238095238,
      "loss": 0.041,
      "step": 182
    },
    {
      "epoch": 13.2,
      "learning_rate": 0.0008126984126984127,
      "loss": 0.0286,
      "step": 189
    },
    {
      "epoch": 13.4,
      "learning_rate": 0.0008015873015873017,
      "loss": 0.0283,
      "step": 196
    },
    {
      "epoch": 14.2,
      "learning_rate": 0.0007904761904761905,
      "loss": 0.0153,
      "step": 203
    },
    {
      "epoch": 14.4,
      "learning_rate": 0.0007793650793650794,
      "loss": 0.0194,
      "step": 210
    },
    {
      "epoch": 15.2,
      "learning_rate": 0.0007682539682539683,
      "loss": 0.0115,
      "step": 217
    },
    {
      "epoch": 15.4,
      "learning_rate": 0.0007571428571428572,
      "loss": 0.011,
      "step": 224
    },
    {
      "epoch": 16.2,
      "learning_rate": 0.000746031746031746,
      "loss": 0.0072,
      "step": 231
    },
    {
      "epoch": 16.4,
      "learning_rate": 0.000734920634920635,
      "loss": 0.0132,
      "step": 238
    },
    {
      "epoch": 17.2,
      "learning_rate": 0.0007238095238095238,
      "loss": 0.0065,
      "step": 245
    },
    {
      "epoch": 17.4,
      "learning_rate": 0.0007126984126984128,
      "loss": 0.0109,
      "step": 252
    },
    {
      "epoch": 18.2,
      "learning_rate": 0.0007015873015873015,
      "loss": 0.0064,
      "step": 259
    },
    {
      "epoch": 18.4,
      "learning_rate": 0.0006904761904761905,
      "loss": 0.0076,
      "step": 266
    },
    {
      "epoch": 19.2,
      "learning_rate": 0.0006793650793650794,
      "loss": 0.0028,
      "step": 273
    },
    {
      "epoch": 19.4,
      "learning_rate": 0.0006682539682539683,
      "loss": 0.0065,
      "step": 280
    }
  ],
  "logging_steps": 7,
  "max_steps": 700,
  "num_train_epochs": 20,
  "save_steps": 500,
  "total_flos": 1.13811835060224e+16,
  "trial_name": null,
  "trial_params": null
}