{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.018369690011481057,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004592422502870264,
      "grad_norm": 22.404470443725586,
      "learning_rate": 1e-05,
      "loss": 103.0343,
      "step": 1
    },
    {
      "epoch": 0.004592422502870264,
      "eval_loss": 6.589047431945801,
      "eval_runtime": 179.7822,
      "eval_samples_per_second": 2.041,
      "eval_steps_per_second": 1.023,
      "step": 1
    },
    {
      "epoch": 0.009184845005740528,
      "grad_norm": 23.372804641723633,
      "learning_rate": 2e-05,
      "loss": 106.0459,
      "step": 2
    },
    {
      "epoch": 0.009184845005740528,
      "eval_loss": 6.456647872924805,
      "eval_runtime": 158.4095,
      "eval_samples_per_second": 2.317,
      "eval_steps_per_second": 1.162,
      "step": 2
    },
    {
      "epoch": 0.013777267508610792,
      "grad_norm": 23.370132446289062,
      "learning_rate": 3e-05,
      "loss": 106.701,
      "step": 3
    },
    {
      "epoch": 0.018369690011481057,
      "grad_norm": 25.078439712524414,
      "learning_rate": 4e-05,
      "loss": 106.0416,
      "step": 4
    },
    {
      "epoch": 0.018369690011481057,
      "eval_loss": NaN,
      "eval_runtime": 161.5216,
      "eval_samples_per_second": 2.272,
      "eval_steps_per_second": 1.139,
      "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": 5065958888570880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}