{
  "best_metric": 0.7326732673267327,
  "best_model_checkpoint": "distilhubert-finetuned-not-a-word2/run-5/checkpoint-24",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 24,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21,
      "grad_norm": 1.6560618877410889,
      "learning_rate": 9.928194518007172e-07,
      "loss": 0.6997,
      "step": 5
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.6409028768539429,
      "learning_rate": 1.9856389036014343e-06,
      "loss": 0.6971,
      "step": 10
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.6359347105026245,
      "learning_rate": 2.978458355402151e-06,
      "loss": 0.6953,
      "step": 15
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.56245756149292,
      "learning_rate": 3.971277807202869e-06,
      "loss": 0.6889,
      "step": 20
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.7326732673267327,
      "eval_loss": 0.6865768432617188,
      "eval_runtime": 1.3652,
      "eval_samples_per_second": 46.879,
      "eval_steps_per_second": 5.86,
      "step": 24
    }
  ],
  "logging_steps": 5,
  "max_steps": 240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 670768569859200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 4.765533368643442e-06,
    "per_device_train_batch_size": 8
  }
}