{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 21,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_runtime": 6.3191,
      "eval_samples_per_second": 4.115,
      "eval_steps_per_second": 0.633,
      "step": 7
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 2.713655710220337,
      "learning_rate": 9e-06,
      "loss": 1.1323,
      "mean_token_accuracy": 0.7305696512523451,
      "num_tokens": 76750.0,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_runtime": 1.168,
      "eval_samples_per_second": 22.26,
      "eval_steps_per_second": 3.425,
      "step": 14
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 2.715928554534912,
      "learning_rate": 1.9e-05,
      "loss": 1.0868,
      "mean_token_accuracy": 0.7391616702079773,
      "num_tokens": 153781.0,
      "step": 20
    },
    {
      "epoch": 3.0,
      "eval_runtime": 1.1537,
      "eval_samples_per_second": 22.535,
      "eval_steps_per_second": 3.467,
      "step": 21
    },
    {
      "epoch": 3.0,
      "step": 21,
      "total_flos": 0.0,
      "train_loss": 0.0,
      "train_runtime": 0.0138,
      "train_samples_per_second": 22453.136,
      "train_steps_per_second": 1525.941
    }
  ],
  "logging_steps": 10,
  "max_steps": 21,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}