{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.211050087213516,
      "epoch": 0.4,
      "grad_norm": 3.0342631340026855,
      "learning_rate": 0.0001794871794871795,
      "loss": 5.019304656982422,
      "mean_token_accuracy": 0.33383559435606003,
      "num_tokens": 805.0,
      "step": 5
    },
    {
      "entropy": 2.6462666034698485,
      "epoch": 0.8,
      "grad_norm": 1.7210749387741089,
      "learning_rate": 0.00015384615384615385,
      "loss": 3.432537841796875,
      "mean_token_accuracy": 0.4346353054046631,
      "num_tokens": 1577.0,
      "step": 10
    }
  ],
  "logging_steps": 5,
  "max_steps": 39,
  "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": 43437495085056.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}