{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000709685431932296,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001419370863864592,
      "grad_norm": 0.4370461106300354,
      "learning_rate": 1e-05,
      "loss": 1.8484,
      "step": 1
    },
    {
      "epoch": 0.0001419370863864592,
      "eval_loss": 1.850610613822937,
      "eval_runtime": 608.3742,
      "eval_samples_per_second": 19.504,
      "eval_steps_per_second": 9.752,
      "step": 1
    },
    {
      "epoch": 0.0002838741727729184,
      "grad_norm": 0.2930557131767273,
      "learning_rate": 2e-05,
      "loss": 1.6568,
      "step": 2
    },
    {
      "epoch": 0.0002838741727729184,
      "eval_loss": 1.8423376083374023,
      "eval_runtime": 447.6405,
      "eval_samples_per_second": 26.508,
      "eval_steps_per_second": 13.254,
      "step": 2
    },
    {
      "epoch": 0.0004258112591593776,
      "grad_norm": 0.3402392864227295,
      "learning_rate": 3e-05,
      "loss": 1.7454,
      "step": 3
    },
    {
      "epoch": 0.0005677483455458368,
      "grad_norm": 0.30549994111061096,
      "learning_rate": 4e-05,
      "loss": 1.6673,
      "step": 4
    },
    {
      "epoch": 0.0005677483455458368,
      "eval_loss": 1.8332293033599854,
      "eval_runtime": 447.5102,
      "eval_samples_per_second": 26.516,
      "eval_steps_per_second": 13.258,
      "step": 4
    },
    {
      "epoch": 0.000709685431932296,
      "grad_norm": 0.4120770990848541,
      "learning_rate": 5e-05,
      "loss": 1.7774,
      "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": 1297193034055680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}