{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1,
  "global_step": 1,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 1.1037,
      "step": 1
    },
    {
      "epoch": 1.0,
      "eval_loss": 4.333573341369629,
      "eval_runtime": 0.036,
      "eval_samples_per_second": 55.487,
      "eval_steps_per_second": 27.744,
      "step": 1
    },
    {
      "epoch": 1.0,
      "step": 1,
      "total_flos": 576049352400.0,
      "train_loss": 1.1036854982376099,
      "train_runtime": 21.068,
      "train_samples_per_second": 0.38,
      "train_steps_per_second": 0.047
    }
  ],
  "logging_steps": 1,
  "max_steps": 1,
  "num_train_epochs": 1,
  "save_steps": 20,
  "total_flos": 576049352400.0,
  "trial_name": null,
  "trial_params": null
}