{ "results": { "webqs": { "acc": 0.022637795275590553, "acc_stderr": 0.0033005770276179373 }, "headqa_en": { "acc": 0.31181619256017507, "acc_stderr": 0.008848039223989218, "acc_norm": 0.35557986870897157, "acc_norm_stderr": 0.009143208309033068 }, "squad2": { "exact": 7.816053230017687, "f1": 12.640343596838946, "HasAns_exact": 14.84480431848853, "HasAns_f1": 24.507219892926596, "NoAns_exact": 0.8074011774600505, "NoAns_f1": 0.8074011774600505, "best_exact": 50.07159100480081, "best_f1": 50.07159100480081 }, "truthfulqa_mc": { "mc1": 0.22399020807833536, "mc1_stderr": 0.014594964329474202, "mc2": 0.38898018897492265, "mc2_stderr": 0.014014176010735629 }, "triviaqa": { "acc": 0.055246176964554056, "acc_stderr": 0.0021480319949071717 }, "headqa_es": { "acc": 0.29540481400437635, "acc_stderr": 0.008714131357853837, "acc_norm": 0.34318016046681254, "acc_norm_stderr": 0.009068379779817705 }, "logiqa": { "acc": 0.20276497695852536, "acc_stderr": 0.015770046635584564, "acc_norm": 0.28110599078341014, "acc_norm_stderr": 0.017632374626460005 } }, "versions": { "webqs": 0, "headqa_en": 0, "squad2": 1, "truthfulqa_mc": 1, "triviaqa": 1, "headqa_es": 0, "logiqa": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=bigscience/bloom-7b1,use_accelerate=True", "num_fewshot": 0, "batch_size": "auto", "device": "cuda:0", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }