{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.044137931034482755,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011034482758620689,
      "grad_norm": 2.924062728881836,
      "learning_rate": 1e-05,
      "loss": 14.0511,
      "step": 1
    },
    {
      "epoch": 0.011034482758620689,
      "eval_loss": 13.964393615722656,
      "eval_runtime": 161.4911,
      "eval_samples_per_second": 0.947,
      "eval_steps_per_second": 0.477,
      "step": 1
    },
    {
      "epoch": 0.022068965517241378,
      "grad_norm": 2.827735424041748,
      "learning_rate": 2e-05,
      "loss": 14.0312,
      "step": 2
    },
    {
      "epoch": 0.022068965517241378,
      "eval_loss": 13.84832763671875,
      "eval_runtime": 4.2428,
      "eval_samples_per_second": 36.061,
      "eval_steps_per_second": 18.148,
      "step": 2
    },
    {
      "epoch": 0.03310344827586207,
      "grad_norm": 2.8996269702911377,
      "learning_rate": 3e-05,
      "loss": 13.6811,
      "step": 3
    },
    {
      "epoch": 0.044137931034482755,
      "grad_norm": 3.0916175842285156,
      "learning_rate": 4e-05,
      "loss": 14.1368,
      "step": 4
    },
    {
      "epoch": 0.044137931034482755,
      "eval_loss": 13.764532089233398,
      "eval_runtime": 4.2543,
      "eval_samples_per_second": 35.963,
      "eval_steps_per_second": 18.099,
      "step": 4
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3528837993332736.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}