{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 2.7706284523010254,
      "learning_rate": 0.0002,
      "loss": 1.8308,
      "mean_token_accuracy": 0.5791758120059967,
      "num_tokens": 7409.0,
      "step": 10
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.0333809852600098,
      "learning_rate": 0.0002,
      "loss": 1.4972,
      "mean_token_accuracy": 0.628404724597931,
      "num_tokens": 13779.0,
      "step": 20
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.8823832273483276,
      "learning_rate": 0.0002,
      "loss": 1.5076,
      "mean_token_accuracy": 0.622391939163208,
      "num_tokens": 21409.0,
      "step": 30
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.6391931772232056,
      "learning_rate": 0.0002,
      "loss": 1.4429,
      "mean_token_accuracy": 0.6252864122390747,
      "num_tokens": 29177.0,
      "step": 40
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.225527286529541,
      "learning_rate": 0.0002,
      "loss": 1.4467,
      "mean_token_accuracy": 0.626051527261734,
      "num_tokens": 35307.0,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.4357553720474243,
      "eval_mean_token_accuracy": 0.6278730299737718,
      "eval_num_tokens": 35307.0,
      "eval_runtime": 17.3781,
      "eval_samples_per_second": 1.956,
      "eval_steps_per_second": 0.518,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1629499865530368.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}