{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07585335018963338,
  "eval_steps": 10,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.116106641292572,
      "epoch": 0.07585335018963338,
      "grad_norm": 1.4921875,
      "learning_rate": 5.6250000000000005e-05,
      "loss": 2.914295959472656,
      "mean_token_accuracy": 0.5410080701112747,
      "num_tokens": 36823.0,
      "step": 10
    },
    {
      "epoch": 0.07585335018963338,
      "eval_entropy": 2.552819073200226,
      "eval_loss": 2.6676909923553467,
      "eval_mean_token_accuracy": 0.5321294479072094,
      "eval_num_tokens": 36823.0,
      "eval_runtime": 14.7674,
      "eval_samples_per_second": 0.542,
      "eval_steps_per_second": 0.542,
      "step": 10
    }
  ],
  "logging_steps": 10,
  "max_steps": 528,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 633512120727552.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}