{
  "results": {
    "coqa": {
      "f1": 0.7650867255895625,
      "f1_stderr": 0.01481717694356494,
      "em": 0.6301666666666667,
      "em_stderr": 0.018680205213012713
    },
    "drop": {
      "em": 0.03429110738255033,
      "em_stderr": 0.0018636035184959787,
      "f1": 0.1338569630872482,
      "f1_stderr": 0.0025165760673094154
    },
    "race": {
      "acc": 0.3866028708133971,
      "acc_stderr": 0.01507138477304713
    }
  },
  "versions": {
    "coqa": 1,
    "drop": 1,
    "race": 1
  },
  "config": {
    "model": "hf-causal-experimental",
    "model_args": "pretrained=mosaicml/mpt-7b,trust_remote_code=True",
    "num_fewshot": 0,
    "batch_size": "auto",
    "device": "cuda",
    "no_cache": true,
    "limit": null,
    "bootstrap_iters": 100000,
    "description_dict": {}
  }
}