{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0002486835315548316,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.9736706310966324e-05,
      "grad_norm": 63.70762252807617,
      "learning_rate": 1e-05,
      "loss": 18.4785,
      "step": 1
    },
    {
      "epoch": 4.9736706310966324e-05,
      "eval_loss": 1.177413821220398,
      "eval_runtime": 1266.8335,
      "eval_samples_per_second": 26.73,
      "eval_steps_per_second": 13.366,
      "step": 1
    },
    {
      "epoch": 9.947341262193265e-05,
      "grad_norm": 66.46443176269531,
      "learning_rate": 2e-05,
      "loss": 18.0286,
      "step": 2
    },
    {
      "epoch": 9.947341262193265e-05,
      "eval_loss": 1.109844446182251,
      "eval_runtime": 1628.2111,
      "eval_samples_per_second": 20.798,
      "eval_steps_per_second": 10.399,
      "step": 2
    },
    {
      "epoch": 0.00014921011893289897,
      "grad_norm": 58.610992431640625,
      "learning_rate": 3e-05,
      "loss": 17.7949,
      "step": 3
    },
    {
      "epoch": 0.0001989468252438653,
      "grad_norm": 49.35665512084961,
      "learning_rate": 4e-05,
      "loss": 16.4268,
      "step": 4
    },
    {
      "epoch": 0.0001989468252438653,
      "eval_loss": 0.9661396741867065,
      "eval_runtime": 1367.892,
      "eval_samples_per_second": 24.756,
      "eval_steps_per_second": 12.378,
      "step": 4
    },
    {
      "epoch": 0.0002486835315548316,
      "grad_norm": 49.56589889526367,
      "learning_rate": 5e-05,
      "loss": 15.3462,
      "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": 4644580267917312.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}