{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.4,
  "eval_steps": 500,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.0689,
      "step": 3
    },
    {
      "epoch": 1.6,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 2.0904,
      "step": 6
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0,
      "loss": 2.1121,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 9,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2926588232466432.0,
  "trial_name": null,
  "trial_params": null
}