{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00704659561349423,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014093191226988461,
      "grad_norm": 20.925233840942383,
      "learning_rate": 1e-05,
      "loss": 13.155,
      "step": 1
    },
    {
      "epoch": 0.0014093191226988461,
      "eval_loss": 13.603864669799805,
      "eval_runtime": 212.4863,
      "eval_samples_per_second": 5.624,
      "eval_steps_per_second": 2.814,
      "step": 1
    },
    {
      "epoch": 0.0028186382453976922,
      "grad_norm": 18.879552841186523,
      "learning_rate": 2e-05,
      "loss": 13.4341,
      "step": 2
    },
    {
      "epoch": 0.0028186382453976922,
      "eval_loss": 13.357934951782227,
      "eval_runtime": 67.4198,
      "eval_samples_per_second": 17.725,
      "eval_steps_per_second": 8.87,
      "step": 2
    },
    {
      "epoch": 0.0042279573680965386,
      "grad_norm": 18.91469955444336,
      "learning_rate": 3e-05,
      "loss": 13.9834,
      "step": 3
    },
    {
      "epoch": 0.0056372764907953845,
      "grad_norm": 20.38007354736328,
      "learning_rate": 4e-05,
      "loss": 12.909,
      "step": 4
    },
    {
      "epoch": 0.0056372764907953845,
      "eval_loss": 12.779269218444824,
      "eval_runtime": 70.1198,
      "eval_samples_per_second": 17.042,
      "eval_steps_per_second": 8.528,
      "step": 4
    },
    {
      "epoch": 0.00704659561349423,
      "grad_norm": 20.616239547729492,
      "learning_rate": 5e-05,
      "loss": 12.7332,
      "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": 4013291974164480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}