{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1038,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.45,
      "learning_rate": 2.5915221579961463e-05,
      "loss": 1.6863,
      "step": 500
    },
    {
      "epoch": 2.89,
      "learning_rate": 1.8304431599229288e-06,
      "loss": 0.9928,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "step": 1038,
      "total_flos": 2.602335381127373e+16,
      "train_loss": 1.3245489601914364,
      "train_runtime": 732.568,
      "train_samples_per_second": 362.522,
      "train_steps_per_second": 1.417
    }
  ],
  "logging_steps": 500,
  "max_steps": 1038,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2.602335381127373e+16,
  "trial_name": null,
  "trial_params": null
}