{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.029465930018416207,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005893186003683241,
      "grad_norm": 0.009900328703224659,
      "learning_rate": 1e-05,
      "loss": 11.936,
      "step": 1
    },
    {
      "epoch": 0.005893186003683241,
      "eval_loss": 11.931907653808594,
      "eval_runtime": 10.2012,
      "eval_samples_per_second": 28.036,
      "eval_steps_per_second": 14.018,
      "step": 1
    },
    {
      "epoch": 0.011786372007366482,
      "grad_norm": 0.00854524690657854,
      "learning_rate": 2e-05,
      "loss": 11.934,
      "step": 2
    },
    {
      "epoch": 0.011786372007366482,
      "eval_loss": 11.931906700134277,
      "eval_runtime": 1.2459,
      "eval_samples_per_second": 229.56,
      "eval_steps_per_second": 114.78,
      "step": 2
    },
    {
      "epoch": 0.017679558011049725,
      "grad_norm": 0.0086208526045084,
      "learning_rate": 3e-05,
      "loss": 11.9322,
      "step": 3
    },
    {
      "epoch": 0.023572744014732964,
      "grad_norm": 0.007165828719735146,
      "learning_rate": 4e-05,
      "loss": 11.933,
      "step": 4
    },
    {
      "epoch": 0.023572744014732964,
      "eval_loss": 11.931904792785645,
      "eval_runtime": 1.2344,
      "eval_samples_per_second": 231.683,
      "eval_steps_per_second": 115.841,
      "step": 4
    },
    {
      "epoch": 0.029465930018416207,
      "grad_norm": 0.010117492638528347,
      "learning_rate": 5e-05,
      "loss": 11.9335,
      "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": 2392768512.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}