{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004271906872430181,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008543813744860362,
      "grad_norm": 2.140207290649414,
      "learning_rate": 1e-05,
      "loss": 3.7483,
      "step": 1
    },
    {
      "epoch": 0.0008543813744860362,
      "eval_loss": 3.831298828125,
      "eval_runtime": 76.0,
      "eval_samples_per_second": 25.947,
      "eval_steps_per_second": 12.974,
      "step": 1
    },
    {
      "epoch": 0.0017087627489720725,
      "grad_norm": 2.0309553146362305,
      "learning_rate": 2e-05,
      "loss": 3.9117,
      "step": 2
    },
    {
      "epoch": 0.0017087627489720725,
      "eval_loss": 3.8123364448547363,
      "eval_runtime": 25.7684,
      "eval_samples_per_second": 76.528,
      "eval_steps_per_second": 38.264,
      "step": 2
    },
    {
      "epoch": 0.0025631441234581086,
      "grad_norm": 1.9071567058563232,
      "learning_rate": 3e-05,
      "loss": 3.7094,
      "step": 3
    },
    {
      "epoch": 0.003417525497944145,
      "grad_norm": 2.0027599334716797,
      "learning_rate": 4e-05,
      "loss": 3.9533,
      "step": 4
    },
    {
      "epoch": 0.003417525497944145,
      "eval_loss": 3.7670953273773193,
      "eval_runtime": 25.8408,
      "eval_samples_per_second": 76.313,
      "eval_steps_per_second": 38.157,
      "step": 4
    },
    {
      "epoch": 0.004271906872430181,
      "grad_norm": 1.9731320142745972,
      "learning_rate": 5e-05,
      "loss": 3.7226,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1309353097297920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}