{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003337644457424173,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006675288914848345,
      "grad_norm": 6.362696170806885,
      "learning_rate": 1e-05,
      "loss": 1.021,
      "step": 1
    },
    {
      "epoch": 0.0006675288914848345,
      "eval_loss": 1.0831050872802734,
      "eval_runtime": 67.5005,
      "eval_samples_per_second": 37.392,
      "eval_steps_per_second": 18.696,
      "step": 1
    },
    {
      "epoch": 0.001335057782969669,
      "grad_norm": 8.773215293884277,
      "learning_rate": 2e-05,
      "loss": 1.0839,
      "step": 2
    },
    {
      "epoch": 0.001335057782969669,
      "eval_loss": 1.0176575183868408,
      "eval_runtime": 28.1888,
      "eval_samples_per_second": 89.539,
      "eval_steps_per_second": 44.769,
      "step": 2
    },
    {
      "epoch": 0.0020025866744545037,
      "grad_norm": 5.226171016693115,
      "learning_rate": 3e-05,
      "loss": 0.9729,
      "step": 3
    },
    {
      "epoch": 0.002670115565939338,
      "grad_norm": 4.828470230102539,
      "learning_rate": 4e-05,
      "loss": 0.9853,
      "step": 4
    },
    {
      "epoch": 0.002670115565939338,
      "eval_loss": 0.9051417112350464,
      "eval_runtime": 28.4605,
      "eval_samples_per_second": 88.684,
      "eval_steps_per_second": 44.342,
      "step": 4
    },
    {
      "epoch": 0.003337644457424173,
      "grad_norm": 2.7432193756103516,
      "learning_rate": 5e-05,
      "loss": 0.8877,
      "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": 356152655216640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}