{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 48,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.533333333333333,
      "grad_norm": 5.249508857727051,
      "learning_rate": 6.9920054492312086e-06,
      "loss": 2.9591,
      "step": 20
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.1078169345855713,
      "learning_rate": 9.151505349477901e-07,
      "loss": 1.0116,
      "step": 40
    },
    {
      "epoch": 6.0,
      "step": 48,
      "total_flos": 1.2470317284851712e+17,
      "train_loss": 1.7898056308428447,
      "train_runtime": 631.4244,
      "train_samples_per_second": 4.542,
      "train_steps_per_second": 0.076
    }
  ],
  "logging_steps": 20,
  "max_steps": 48,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2470317284851712e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}