{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008523219113318861,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021308047783297153,
      "grad_norm": 18.833036422729492,
      "learning_rate": 1e-05,
      "loss": 8.7482,
      "step": 1
    },
    {
      "epoch": 0.00021308047783297153,
      "eval_loss": 8.408291816711426,
      "eval_runtime": 202.7276,
      "eval_samples_per_second": 38.993,
      "eval_steps_per_second": 19.499,
      "step": 1
    },
    {
      "epoch": 0.00042616095566594305,
      "grad_norm": 14.874626159667969,
      "learning_rate": 2e-05,
      "loss": 8.0443,
      "step": 2
    },
    {
      "epoch": 0.00042616095566594305,
      "eval_loss": 8.203876495361328,
      "eval_runtime": 104.7813,
      "eval_samples_per_second": 75.443,
      "eval_steps_per_second": 37.726,
      "step": 2
    },
    {
      "epoch": 0.0006392414334989146,
      "grad_norm": 15.174580574035645,
      "learning_rate": 3e-05,
      "loss": 8.316,
      "step": 3
    },
    {
      "epoch": 0.0008523219113318861,
      "grad_norm": 13.973289489746094,
      "learning_rate": 4e-05,
      "loss": 7.6847,
      "step": 4
    },
    {
      "epoch": 0.0008523219113318861,
      "eval_loss": 7.609894752502441,
      "eval_runtime": 104.9595,
      "eval_samples_per_second": 75.315,
      "eval_steps_per_second": 37.662,
      "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": 1162509759283200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}