{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018626309662398137,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0037252619324796275,
      "grad_norm": 67.76799774169922,
      "learning_rate": 1e-05,
      "loss": 128.9905,
      "step": 1
    },
    {
      "epoch": 0.0037252619324796275,
      "eval_loss": NaN,
      "eval_runtime": 200.5957,
      "eval_samples_per_second": 2.258,
      "eval_steps_per_second": 1.132,
      "step": 1
    },
    {
      "epoch": 0.007450523864959255,
      "grad_norm": 70.9619140625,
      "learning_rate": 2e-05,
      "loss": 149.4326,
      "step": 2
    },
    {
      "epoch": 0.007450523864959255,
      "eval_loss": NaN,
      "eval_runtime": 41.7188,
      "eval_samples_per_second": 10.858,
      "eval_steps_per_second": 5.441,
      "step": 2
    },
    {
      "epoch": 0.011175785797438883,
      "grad_norm": 61.16599655151367,
      "learning_rate": 3e-05,
      "loss": 136.7895,
      "step": 3
    },
    {
      "epoch": 0.01490104772991851,
      "grad_norm": 58.64887237548828,
      "learning_rate": 4e-05,
      "loss": 125.9775,
      "step": 4
    },
    {
      "epoch": 0.01490104772991851,
      "eval_loss": NaN,
      "eval_runtime": 19.5158,
      "eval_samples_per_second": 23.212,
      "eval_steps_per_second": 11.632,
      "step": 4
    },
    {
      "epoch": 0.018626309662398137,
      "grad_norm": 71.09612274169922,
      "learning_rate": 5e-05,
      "loss": 136.0768,
      "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": 6270684581855232.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}