{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 308,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 0.37675046920776367,
      "learning_rate": 0.0001681818181818182,
      "loss": 1.7515,
      "mean_token_accuracy": 0.6049755607545376,
      "num_tokens": 204800.0,
      "step": 50
    },
    {
      "epoch": 0.3252032520325203,
      "grad_norm": 0.3089984357357025,
      "learning_rate": 0.00013571428571428572,
      "loss": 1.3323,
      "mean_token_accuracy": 0.6925122183561325,
      "num_tokens": 409600.0,
      "step": 100
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 0.3363010883331299,
      "learning_rate": 0.00010324675324675325,
      "loss": 1.2756,
      "mean_token_accuracy": 0.7040957960486413,
      "num_tokens": 614400.0,
      "step": 150
    },
    {
      "epoch": 0.6504065040650406,
      "grad_norm": 0.335611492395401,
      "learning_rate": 7.077922077922077e-05,
      "loss": 1.2833,
      "mean_token_accuracy": 0.7033577680587768,
      "num_tokens": 819200.0,
      "step": 200
    },
    {
      "epoch": 0.8130081300813008,
      "grad_norm": 0.3524633049964905,
      "learning_rate": 3.831168831168831e-05,
      "loss": 1.2286,
      "mean_token_accuracy": 0.7145161288976669,
      "num_tokens": 1024000.0,
      "step": 250
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.34292736649513245,
      "learning_rate": 5.844155844155844e-06,
      "loss": 1.2549,
      "mean_token_accuracy": 0.7073900297284126,
      "num_tokens": 1228800.0,
      "step": 300
    }
  ],
  "logging_steps": 50,
  "max_steps": 308,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.09971568443392e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}