{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 33,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.09755474978592246,
      "epoch": 0.3065134099616858,
      "grad_norm": 1.1475945711135864,
      "learning_rate": 7.741935483870968e-05,
      "loss": 0.1013,
      "mean_token_accuracy": 0.9755499251186848,
      "num_tokens": 43701.0,
      "step": 10
    },
    {
      "entropy": 0.07863486893475055,
      "epoch": 0.6130268199233716,
      "grad_norm": 0.7989944815635681,
      "learning_rate": 4.516129032258064e-05,
      "loss": 0.078,
      "mean_token_accuracy": 0.9832243904471397,
      "num_tokens": 87431.0,
      "step": 20
    },
    {
      "entropy": 0.0735241130925715,
      "epoch": 0.9195402298850575,
      "grad_norm": 0.6291962265968323,
      "learning_rate": 1.2903225806451613e-05,
      "loss": 0.0563,
      "mean_token_accuracy": 0.9856645412743091,
      "num_tokens": 131172.0,
      "step": 30
    }
  ],
  "logging_steps": 10,
  "max_steps": 33,
  "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": 310619179605504.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}