{
  "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": 1.2876,
      "step": 500
    },
    {
      "epoch": 5.0,
      "step": 785,
      "total_flos": 4899314188800000.0,
      "train_loss": 0.9167267234462082,
      "train_runtime": 215.6037,
      "train_samples_per_second": 115.953,
      "train_steps_per_second": 3.641
    }
  ],
  "logging_steps": 500,
  "max_steps": 785,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 4899314188800000.0,
  "trial_name": null,
  "trial_params": null
}