{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 20.0,
  "global_step": 720,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 13.89,
      "learning_rate": 1.527777777777778e-05,
      "loss": 1.9478,
      "step": 500
    },
    {
      "epoch": 20.0,
      "step": 720,
      "total_flos": 1860399267840000.0,
      "train_loss": 1.8756726582845051,
      "train_runtime": 674.4182,
      "train_samples_per_second": 5.279,
      "train_steps_per_second": 1.068
    }
  ],
  "max_steps": 720,
  "num_train_epochs": 20,
  "total_flos": 1860399267840000.0,
  "trial_name": null,
  "trial_params": null
}