{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 45,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11,
      "learning_rate": 0.0,
      "loss": 1.8683,
      "step": 1
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 1.3275,
      "step": 2
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.4462,
      "step": 3
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 1.2039,
      "step": 4
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 1.1195,
      "step": 5
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0002,
      "loss": 1.0235,
      "step": 6
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 0.977,
      "step": 7
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 0.8402,
      "step": 8
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0002,
      "loss": 0.8774,
      "step": 9
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.023256778717041,
      "eval_runtime": 5.1515,
      "eval_samples_per_second": 9.706,
      "eval_steps_per_second": 0.388,
      "step": 9
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 0.663,
      "step": 10
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0002,
      "loss": 0.4821,
      "step": 11
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 0.4614,
      "step": 12
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002,
      "loss": 0.5169,
      "step": 13
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0002,
      "loss": 0.4671,
      "step": 14
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 0.4509,
      "step": 15
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0002,
      "loss": 0.3006,
      "step": 16
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 0.2702,
      "step": 17
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0002,
      "loss": 0.2187,
      "step": 18
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.1222225427627563,
      "eval_runtime": 5.1565,
      "eval_samples_per_second": 9.696,
      "eval_steps_per_second": 0.388,
      "step": 18
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0002,
      "loss": 0.1543,
      "step": 19
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0002,
      "loss": 0.105,
      "step": 20
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0002,
      "loss": 0.0996,
      "step": 21
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0002,
      "loss": 0.1239,
      "step": 22
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0002,
      "loss": 0.0898,
      "step": 23
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0002,
      "loss": 0.0557,
      "step": 24
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0002,
      "loss": 0.0948,
      "step": 25
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0002,
      "loss": 0.098,
      "step": 26
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0002,
      "loss": 0.0704,
      "step": 27
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.183333396911621,
      "eval_runtime": 5.3107,
      "eval_samples_per_second": 9.415,
      "eval_steps_per_second": 0.377,
      "step": 27
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.0002,
      "loss": 0.0357,
      "step": 28
    },
    {
      "epoch": 3.22,
      "learning_rate": 0.0002,
      "loss": 0.0341,
      "step": 29
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.0002,
      "loss": 0.0406,
      "step": 30
    },
    {
      "epoch": 3.44,
      "learning_rate": 0.0002,
      "loss": 0.0258,
      "step": 31
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.0002,
      "loss": 0.0342,
      "step": 32
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.0002,
      "loss": 0.0333,
      "step": 33
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.0002,
      "loss": 0.0317,
      "step": 34
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.0002,
      "loss": 0.04,
      "step": 35
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0002,
      "loss": 0.0295,
      "step": 36
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.370598554611206,
      "eval_runtime": 5.2178,
      "eval_samples_per_second": 9.582,
      "eval_steps_per_second": 0.383,
      "step": 36
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.0002,
      "loss": 0.0114,
      "step": 37
    },
    {
      "epoch": 4.22,
      "learning_rate": 0.0002,
      "loss": 0.0181,
      "step": 38
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.0002,
      "loss": 0.0141,
      "step": 39
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.0002,
      "loss": 0.0099,
      "step": 40
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.0002,
      "loss": 0.0085,
      "step": 41
    },
    {
      "epoch": 4.67,
      "learning_rate": 0.0002,
      "loss": 0.0155,
      "step": 42
    },
    {
      "epoch": 4.78,
      "learning_rate": 0.0002,
      "loss": 0.0279,
      "step": 43
    },
    {
      "epoch": 4.89,
      "learning_rate": 0.0002,
      "loss": 0.0094,
      "step": 44
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0002,
      "loss": 0.0129,
      "step": 45
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.4478448629379272,
      "eval_runtime": 5.1693,
      "eval_samples_per_second": 9.672,
      "eval_steps_per_second": 0.387,
      "step": 45
    },
    {
      "epoch": 5.0,
      "step": 45,
      "total_flos": 8.470619890489754e+16,
      "train_loss": 0.3519688956853416,
      "train_runtime": 299.0301,
      "train_samples_per_second": 4.732,
      "train_steps_per_second": 0.15
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 45,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 50000,
  "total_flos": 8.470619890489754e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}