{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0033651149747616375,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005608524957936063,
      "grad_norm": 0.013491886667907238,
      "learning_rate": 2e-05,
      "loss": 11.9315,
      "step": 1
    },
    {
      "epoch": 0.0005608524957936063,
      "eval_loss": 11.931306838989258,
      "eval_runtime": 2.6914,
      "eval_samples_per_second": 279.032,
      "eval_steps_per_second": 139.702,
      "step": 1
    },
    {
      "epoch": 0.0011217049915872126,
      "grad_norm": 0.007763075176626444,
      "learning_rate": 4e-05,
      "loss": 11.9304,
      "step": 2
    },
    {
      "epoch": 0.0016825574873808188,
      "grad_norm": 0.012837530113756657,
      "learning_rate": 6e-05,
      "loss": 11.9319,
      "step": 3
    },
    {
      "epoch": 0.0016825574873808188,
      "eval_loss": 11.931303977966309,
      "eval_runtime": 2.7422,
      "eval_samples_per_second": 273.868,
      "eval_steps_per_second": 137.116,
      "step": 3
    },
    {
      "epoch": 0.002243409983174425,
      "grad_norm": 0.015588194131851196,
      "learning_rate": 8e-05,
      "loss": 11.9328,
      "step": 4
    },
    {
      "epoch": 0.0028042624789680315,
      "grad_norm": 0.016935445368289948,
      "learning_rate": 0.0001,
      "loss": 11.9248,
      "step": 5
    },
    {
      "epoch": 0.0033651149747616375,
      "grad_norm": 0.009075427427887917,
      "learning_rate": 0.00012,
      "loss": 11.926,
      "step": 6
    },
    {
      "epoch": 0.0033651149747616375,
      "eval_loss": 11.93128776550293,
      "eval_runtime": 2.8211,
      "eval_samples_per_second": 266.211,
      "eval_steps_per_second": 133.283,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 738508800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}