{
  "results": {
    "kobest_boolq": {
      "acc": 0.594017094017094,
      "acc_stderr": 0.013110658638863893,
      "macro_f1": 0.5766968517264726,
      "macro_f1_stderr": 0.013321751352234396
    },
    "kobest_copa": {
      "acc": 0.796,
      "acc_stderr": 0.012749374359024387,
      "macro_f1": 0.7956042899052566,
      "macro_f1_stderr": 0.012768263930194495
    },
    "kobest_hellaswag": {
      "acc": 0.494,
      "acc_stderr": 0.022381462412439324,
      "acc_norm": 0.586,
      "acc_norm_stderr": 0.02204949796982787,
      "macro_f1": 0.49215887000493286,
      "macro_f1_stderr": 0.02237097469536285
    },
    "kobest_sentineg": {
      "acc": 0.9395465994962217,
      "acc_stderr": 0.01197627988893257,
      "macro_f1": 0.9393430099312452,
      "macro_f1_stderr": 0.012043294700994262
    }
  },
  "versions": {
    "kobest_boolq": 0,
    "kobest_copa": 0,
    "kobest_hellaswag": 0,
    "kobest_sentineg": 0
  },
  "config": {
    "model": "gpt2",
    "model_args": "pretrained=./output",
    "num_fewshot": 10,
    "batch_size": "4",
    "device": "cuda:0",
    "no_cache": true,
    "limit": null,
    "bootstrap_iters": 100000,
    "description_dict": {}
  }
}