{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.8918910471598307,
      "epoch": 1.0,
      "grad_norm": 0.83203125,
      "learning_rate": 0.00016473862847818277,
      "loss": 1.8935,
      "mean_token_accuracy": 0.600308610200882,
      "num_tokens": 75421.0,
      "step": 10
    },
    {
      "entropy": 1.5398784836133321,
      "epoch": 2.0,
      "grad_norm": 0.83984375,
      "learning_rate": 6.298618446600856e-05,
      "loss": 1.5611,
      "mean_token_accuracy": 0.6552372427781423,
      "num_tokens": 150842.0,
      "step": 20
    }
  ],
  "logging_steps": 10,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 890949754871808.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}