{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 33,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.7155912235379218,
      "epoch": 0.7722007722007722,
      "grad_norm": 0.023681640625,
      "learning_rate": 3.6560671583635467e-05,
      "loss": 1.7020303344726562,
      "mean_token_accuracy": 0.6151937894523144,
      "num_tokens": 295911.0,
      "step": 25
    }
  ],
  "logging_steps": 25,
  "max_steps": 33,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.6399036445826048e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}