{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.6666666666666665,
  "eval_steps": 500,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 10.266286948256248,
      "learning_rate": 2e-05,
      "loss": 1.0311,
      "mean_token_accuracy": 0.7977499216794968,
      "num_tokens": 254035.0,
      "step": 1
    },
    {
      "epoch": 2.6666666666666665,
      "mean_token_accuracy": 0.812268191576004,
      "num_tokens": 901286.0,
      "step": 3,
      "total_flos": 2.79086438023168e+16,
      "train_loss": 1.4995660781860352,
      "train_runtime": 25.7852,
      "train_samples_per_second": 5.236,
      "train_steps_per_second": 0.116
    }
  ],
  "logging_steps": 5,
  "max_steps": 3,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.79086438023168e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}