{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 837,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6,
      "learning_rate": 1.850657108721625e-05,
      "loss": 2.9804,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.4562251567840576,
      "eval_runtime": 42.4632,
      "eval_samples_per_second": 42.083,
      "eval_steps_per_second": 5.275,
      "step": 837
    }
  ],
  "logging_steps": 500,
  "max_steps": 6696,
  "num_train_epochs": 8,
  "save_steps": 500,
  "total_flos": 1310836801536000.0,
  "trial_name": null,
  "trial_params": null
}