{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2,
  "eval_steps": 5,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 3.1814,
      "step": 1
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00018571428571428572,
      "loss": 3.5839,
      "step": 2
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00017142857142857143,
      "loss": 3.7658,
      "step": 3
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00015714285714285716,
      "loss": 3.6873,
      "step": 4
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00014285714285714287,
      "loss": 3.6731,
      "step": 5
    },
    {
      "epoch": 0.2,
      "eval_loss": 3.442739963531494,
      "eval_runtime": 53.5168,
      "eval_samples_per_second": 0.187,
      "eval_steps_per_second": 0.037,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 15,
  "num_train_epochs": 1,
  "save_steps": 5,
  "total_flos": 18289914937344.0,
  "trial_name": null,
  "trial_params": null
}