{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7766990291262136,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.3576171875,
      "epoch": 0.1941747572815534,
      "grad_norm": 1.4468644857406616,
      "learning_rate": 0.00019991110182465032,
      "loss": 2.4723321914672853,
      "mean_token_accuracy": 0.48485579565167425,
      "num_tokens": 32726.0,
      "step": 10
    },
    {
      "entropy": 1.86201171875,
      "epoch": 0.3883495145631068,
      "grad_norm": 1.8271902799606323,
      "learning_rate": 0.00019681623029976588,
      "loss": 1.8011039733886718,
      "mean_token_accuracy": 0.6076911687850952,
      "num_tokens": 65640.0,
      "step": 20
    },
    {
      "entropy": 1.4529296875,
      "epoch": 0.5825242718446602,
      "grad_norm": 0.8124955296516418,
      "learning_rate": 0.00018943324918225494,
      "loss": 1.473008918762207,
      "mean_token_accuracy": 0.6781924746930599,
      "num_tokens": 98479.0,
      "step": 30
    },
    {
      "entropy": 1.4251953125,
      "epoch": 0.7766990291262136,
      "grad_norm": 0.6854525208473206,
      "learning_rate": 0.00017808915976161362,
      "loss": 1.3831080436706542,
      "mean_token_accuracy": 0.6932718701660633,
      "num_tokens": 131059.0,
      "step": 40
    }
  ],
  "logging_steps": 10,
  "max_steps": 156,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 409756970919168.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}