{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 62,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 4.128289337456226,
      "epoch": 0.4048582995951417,
      "grad_norm": 0.0302734375,
      "learning_rate": 0.00014067366430758004,
      "loss": 4.230033264160157,
      "mean_token_accuracy": 0.28531623594462874,
      "num_tokens": 180802.0,
      "step": 25
    },
    {
      "entropy": 4.0481261727213855,
      "epoch": 0.8097165991902834,
      "grad_norm": 0.028076171875,
      "learning_rate": 2.2285403854302912e-05,
      "loss": 4.149235534667969,
      "mean_token_accuracy": 0.28714169673621653,
      "num_tokens": 357892.0,
      "step": 50
    }
  ],
  "logging_steps": 25,
  "max_steps": 62,
  "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": 3.731544560214221e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}