{
  "results": {
    "drop": {
      "em": 0.014995805369127516,
      "em_stderr": 0.0012446395261788805,
      "f1": 0.0621245805369127,
      "f1_stderr": 0.001730980795797461
    },
    "coqa": {
      "f1": 0.22712736568843772,
      "f1_stderr": 0.01673094848597647,
      "em": 0.174,
      "em_stderr": 0.016190705499013296
    },
    "race": {
      "acc": 0.30239234449760766,
      "acc_stderr": 0.014214800395178313
    }
  },
  "versions": {
    "drop": 1,
    "race": 1,
    "coqa": 1
  },
  "config": {
    "model": "hf-causal-experimental",
    "model_args": "pretrained=bigscience/bloom-560m,use_accelerate=True",
    "num_fewshot": 0,
    "batch_size": "auto",
    "device": "cuda:0",
    "no_cache": true,
    "limit": null,
    "bootstrap_iters": 100000,
    "description_dict": {}
  }
}