{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 94,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 2.265625,
      "learning_rate": 1.9986594826804563e-05,
      "loss": 0.6304,
      "mean_token_accuracy": 0.840462688356638,
      "num_tokens": 741116.0,
      "step": 10
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 1.71875,
      "learning_rate": 1.9749279121818235e-05,
      "loss": 0.4711,
      "mean_token_accuracy": 0.85478610470891,
      "num_tokens": 1071393.0,
      "step": 20
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.1328125,
      "learning_rate": 1.9222195128618108e-05,
      "loss": 0.4466,
      "mean_token_accuracy": 0.8568335678428411,
      "num_tokens": 1769686.0,
      "step": 30
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 1.1875,
      "learning_rate": 1.842100884922812e-05,
      "loss": 0.4106,
      "mean_token_accuracy": 0.8677616793662309,
      "num_tokens": 2202271.0,
      "step": 40
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 1.09375,
      "learning_rate": 1.7369533159843368e-05,
      "loss": 0.4121,
      "mean_token_accuracy": 0.8662014000117779,
      "num_tokens": 2740643.0,
      "step": 50
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.109375,
      "learning_rate": 1.609902004400073e-05,
      "loss": 0.4144,
      "mean_token_accuracy": 0.8654925987124443,
      "num_tokens": 3248341.0,
      "step": 60
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 0.92578125,
      "learning_rate": 1.4647231720437687e-05,
      "loss": 0.4162,
      "mean_token_accuracy": 0.8661399863660335,
      "num_tokens": 3636141.0,
      "step": 70
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 1.015625,
      "learning_rate": 1.3057318273597531e-05,
      "loss": 0.4167,
      "mean_token_accuracy": 0.8628269486129284,
      "num_tokens": 4344849.0,
      "step": 80
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.4296875,
      "learning_rate": 1.1376535145871685e-05,
      "loss": 0.41,
      "mean_token_accuracy": 0.8684016942977906,
      "num_tokens": 4674072.0,
      "step": 90
    }
  ],
  "logging_steps": 10,
  "max_steps": 188,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.040953374461952e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}