{
  "results": {
    "kobest_boolq": {
      "acc": 0.5968660968660968,
      "acc_stderr": 0.013095867778461178,
      "macro_f1": 0.5304603080064664,
      "macro_f1_stderr": 0.013586196223496537
    },
    "kobest_copa": {
      "acc": 0.794,
      "acc_stderr": 0.012795613612786553,
      "macro_f1": 0.7937326775501048,
      "macro_f1_stderr": 0.012808081534088474
    },
    "kobest_hellaswag": {
      "acc": 0.498,
      "acc_stderr": 0.022382894986483524,
      "acc_norm": 0.59,
      "acc_norm_stderr": 0.022017482578127676,
      "macro_f1": 0.493789564405272,
      "macro_f1_stderr": 0.022368543611080722
    },
    "kobest_sentineg": {
      "acc": 0.9193954659949622,
      "acc_stderr": 0.013679912566808524,
      "macro_f1": 0.9191692965489158,
      "macro_f1_stderr": 0.013704064312276852
    }
  },
  "versions": {
    "kobest_boolq": 0,
    "kobest_copa": 0,
    "kobest_hellaswag": 0,
    "kobest_sentineg": 0
  },
  "config": {
    "model": "gpt2",
    "model_args": "pretrained=/home/work/DeepSpeedExamples/DeepSpeedExamples/applications/DeepSpeed-Chat/training/step3_rlhf_finetuning/output/actor",
    "num_fewshot": 10,
    "batch_size": "8",
    "device": "cuda:0",
    "no_cache": true,
    "limit": null,
    "bootstrap_iters": 100000,
    "description_dict": {}
  }
}