{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 940,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.32,
      "learning_rate": 2.340425531914894e-05,
      "loss": 0.6488,
      "step": 500
    },
    {
      "epoch": 10.0,
      "step": 940,
      "total_flos": 496885570560000.0,
      "train_loss": 0.3617458444960574,
      "train_runtime": 216.5737,
      "train_samples_per_second": 138.521,
      "train_steps_per_second": 4.34
    }
  ],
  "logging_steps": 500,
  "max_steps": 940,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 496885570560000.0,
  "trial_name": null,
  "trial_params": null
}