{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.6666666666666665,
  "eval_steps": 500,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.33,
      "learning_rate": 0.0002,
      "loss": 1.1639,
      "step": 1
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.000175,
      "loss": 1.3083,
      "step": 2
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.2394,
      "step": 3
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.000125,
      "loss": 1.0013,
      "step": 4
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0001,
      "loss": 1.1591,
      "step": 5
    },
    {
      "epoch": 2.67,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.9436,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 9,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 95034271334400.0,
  "trial_name": null,
  "trial_params": null
}