{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.029585798816568046,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005917159763313609,
      "grad_norm": 414.36285400390625,
      "learning_rate": 1e-05,
      "loss": 46.481,
      "step": 1
    },
    {
      "epoch": 0.005917159763313609,
      "eval_loss": 2.746363639831543,
      "eval_runtime": 119.2808,
      "eval_samples_per_second": 2.389,
      "eval_steps_per_second": 1.199,
      "step": 1
    },
    {
      "epoch": 0.011834319526627219,
      "grad_norm": 423.7663269042969,
      "learning_rate": 2e-05,
      "loss": 50.277,
      "step": 2
    },
    {
      "epoch": 0.011834319526627219,
      "eval_loss": 2.383618116378784,
      "eval_runtime": 20.5083,
      "eval_samples_per_second": 13.897,
      "eval_steps_per_second": 6.973,
      "step": 2
    },
    {
      "epoch": 0.01775147928994083,
      "grad_norm": 374.5813903808594,
      "learning_rate": 3e-05,
      "loss": 39.8384,
      "step": 3
    },
    {
      "epoch": 0.023668639053254437,
      "grad_norm": 313.0151062011719,
      "learning_rate": 4e-05,
      "loss": 38.4154,
      "step": 4
    },
    {
      "epoch": 0.023668639053254437,
      "eval_loss": 1.5203543901443481,
      "eval_runtime": 20.5334,
      "eval_samples_per_second": 13.88,
      "eval_steps_per_second": 6.964,
      "step": 4
    },
    {
      "epoch": 0.029585798816568046,
      "grad_norm": 232.3188934326172,
      "learning_rate": 5e-05,
      "loss": 23.5195,
      "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": 3505343598428160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}