{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5657708628005658,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011315417256011316,
      "eval_loss": 10.555892944335938,
      "eval_runtime": 36.4498,
      "eval_samples_per_second": 16.324,
      "eval_steps_per_second": 2.058,
      "step": 1
    },
    {
      "epoch": 0.11315417256011315,
      "grad_norm": 23.465301513671875,
      "learning_rate": 9.330127018922194e-05,
      "loss": 5.9727,
      "step": 10
    },
    {
      "epoch": 0.11315417256011315,
      "eval_loss": 0.7171273827552795,
      "eval_runtime": 37.0437,
      "eval_samples_per_second": 16.062,
      "eval_steps_per_second": 2.025,
      "step": 10
    },
    {
      "epoch": 0.2263083451202263,
      "grad_norm": 2.5606420040130615,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.2816,
      "step": 20
    },
    {
      "epoch": 0.2263083451202263,
      "eval_loss": 0.13300880789756775,
      "eval_runtime": 37.0915,
      "eval_samples_per_second": 16.041,
      "eval_steps_per_second": 2.022,
      "step": 20
    },
    {
      "epoch": 0.33946251768033947,
      "grad_norm": 1.7062979936599731,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.1144,
      "step": 30
    },
    {
      "epoch": 0.33946251768033947,
      "eval_loss": 0.08448273688554764,
      "eval_runtime": 37.1595,
      "eval_samples_per_second": 16.012,
      "eval_steps_per_second": 2.018,
      "step": 30
    },
    {
      "epoch": 0.4526166902404526,
      "grad_norm": 0.8172471523284912,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0911,
      "step": 40
    },
    {
      "epoch": 0.4526166902404526,
      "eval_loss": 0.07390791177749634,
      "eval_runtime": 37.1508,
      "eval_samples_per_second": 16.016,
      "eval_steps_per_second": 2.019,
      "step": 40
    },
    {
      "epoch": 0.5657708628005658,
      "grad_norm": 0.9632566571235657,
      "learning_rate": 0.0,
      "loss": 0.0949,
      "step": 50
    },
    {
      "epoch": 0.5657708628005658,
      "eval_loss": 0.07213994860649109,
      "eval_runtime": 37.0498,
      "eval_samples_per_second": 16.059,
      "eval_steps_per_second": 2.024,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.52887313301504e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}