{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 790,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.33,
      "learning_rate": 1.8354430379746836e-05,
      "loss": 1.2199,
      "step": 500
    },
    {
      "epoch": 10.0,
      "step": 790,
      "total_flos": 4899491251200000.0,
      "train_loss": 0.8420210005361822,
      "train_runtime": 308.0717,
      "train_samples_per_second": 162.3,
      "train_steps_per_second": 2.564
    }
  ],
  "logging_steps": 500,
  "max_steps": 790,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 4899491251200000.0,
  "trial_name": null,
  "trial_params": null
}