{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 785,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.18,
      "learning_rate": 1.8152866242038215e-05,
      "loss": 1.6263,
      "step": 500
    },
    {
      "epoch": 5.0,
      "step": 785,
      "total_flos": 2449745625600000.0,
      "train_loss": 1.1950868934582752,
      "train_runtime": 187.5187,
      "train_samples_per_second": 133.32,
      "train_steps_per_second": 4.186
    }
  ],
  "logging_steps": 500,
  "max_steps": 785,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 2449745625600000.0,
  "trial_name": null,
  "trial_params": null
}