{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "learning_rate": 0.0002,
      "loss": 0.8677,
      "step": 1
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.8677,
      "step": 2
    },
    {
      "epoch": 0.75,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.8009,
      "step": 3
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.7575,
      "step": 4
    }
  ],
  "logging_steps": 1,
  "max_steps": 4,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 325176671600640.0,
  "trial_name": null,
  "trial_params": null
}