{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03062200956937799,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007655502392344498,
      "grad_norm": 1.7012678384780884,
      "learning_rate": 1e-05,
      "loss": 7.5468,
      "step": 1
    },
    {
      "epoch": 0.007655502392344498,
      "eval_loss": 8.355514526367188,
      "eval_runtime": 128.2728,
      "eval_samples_per_second": 1.715,
      "eval_steps_per_second": 0.858,
      "step": 1
    },
    {
      "epoch": 0.015311004784688996,
      "grad_norm": 1.8487701416015625,
      "learning_rate": 2e-05,
      "loss": 8.2374,
      "step": 2
    },
    {
      "epoch": 0.015311004784688996,
      "eval_loss": 8.274739265441895,
      "eval_runtime": 5.045,
      "eval_samples_per_second": 43.608,
      "eval_steps_per_second": 21.804,
      "step": 2
    },
    {
      "epoch": 0.022966507177033493,
      "grad_norm": 2.3434340953826904,
      "learning_rate": 3e-05,
      "loss": 8.6112,
      "step": 3
    },
    {
      "epoch": 0.03062200956937799,
      "grad_norm": 1.7914743423461914,
      "learning_rate": 4e-05,
      "loss": 8.3514,
      "step": 4
    },
    {
      "epoch": 0.03062200956937799,
      "eval_loss": 8.211784362792969,
      "eval_runtime": 5.0586,
      "eval_samples_per_second": 43.49,
      "eval_steps_per_second": 21.745,
      "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": 2875349476048896.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}