{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 56,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.0,
      "loss": 1.4894,
      "step": 1
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 1.2004,
      "step": 2
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0002,
      "loss": 1.1709,
      "step": 3
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 1.0756,
      "step": 4
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 1.039,
      "step": 5
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0002,
      "loss": 0.9718,
      "step": 6
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.922,
      "step": 7
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0002,
      "loss": 0.9097,
      "step": 8
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 0.8924,
      "step": 9
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 0.8943,
      "step": 10
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0002,
      "loss": 0.8296,
      "step": 11
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0002,
      "loss": 0.7891,
      "step": 12
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 0.7679,
      "step": 13
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 0.723,
      "step": 14
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 0.7228,
      "step": 15
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0002,
      "loss": 0.6779,
      "step": 16
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0002,
      "loss": 0.5896,
      "step": 17
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 0.6516,
      "step": 18
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 0.5621,
      "step": 19
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0002,
      "loss": 0.6197,
      "step": 20
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002,
      "loss": 0.4754,
      "step": 21
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0002,
      "loss": 0.4386,
      "step": 22
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 0.4126,
      "step": 23
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 0.3274,
      "step": 24
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 0.3908,
      "step": 25
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 0.3058,
      "step": 26
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0002,
      "loss": 0.3605,
      "step": 27
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.2814,
      "step": 28
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.22194796800613403,
      "eval_runtime": 56.9155,
      "eval_samples_per_second": 15.233,
      "eval_steps_per_second": 0.492,
      "step": 28
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002,
      "loss": 0.2038,
      "step": 29
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 0.2133,
      "step": 30
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 0.1911,
      "step": 31
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0002,
      "loss": 0.1707,
      "step": 32
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0002,
      "loss": 0.1928,
      "step": 33
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 0.1678,
      "step": 34
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 0.2044,
      "step": 35
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 0.1367,
      "step": 36
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0002,
      "loss": 0.1395,
      "step": 37
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.0002,
      "loss": 0.0845,
      "step": 38
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 0.093,
      "step": 39
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 0.1559,
      "step": 40
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.0002,
      "loss": 0.1009,
      "step": 41
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0002,
      "loss": 0.0909,
      "step": 42
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0002,
      "loss": 0.1177,
      "step": 43
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 0.1206,
      "step": 44
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 0.062,
      "step": 45
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0002,
      "loss": 0.0648,
      "step": 46
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002,
      "loss": 0.0793,
      "step": 47
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 0.1064,
      "step": 48
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0002,
      "loss": 0.0924,
      "step": 49
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 0.0518,
      "step": 50
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0002,
      "loss": 0.1159,
      "step": 51
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.0002,
      "loss": 0.0479,
      "step": 52
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 0.1041,
      "step": 53
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0002,
      "loss": 0.1483,
      "step": 54
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0002,
      "loss": 0.0986,
      "step": 55
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0002,
      "loss": 0.0352,
      "step": 56
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.03910892829298973,
      "eval_runtime": 56.8268,
      "eval_samples_per_second": 15.257,
      "eval_steps_per_second": 0.493,
      "step": 56
    },
    {
      "epoch": 2.0,
      "step": 56,
      "total_flos": 1.65447188707541e+17,
      "train_loss": 0.42645503600527135,
      "train_runtime": 568.7271,
      "train_samples_per_second": 3.049,
      "train_steps_per_second": 0.098
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 56,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50000,
  "total_flos": 1.65447188707541e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}