{ "results": { "logiqa": { "acc": 0.22580645161290322, "acc_stderr": 0.01639971378844507, "acc_norm": 0.271889400921659, "acc_norm_stderr": 0.01745171600943683 }, "webqs": { "acc": 0.008366141732283465, "acc_stderr": 0.002021079144496907 }, "triviaqa": { "acc": 0.014408202952355696, "acc_stderr": 0.001120427476389321 }, "truthfulqa_mc": { "mc1": 0.24479804161566707, "mc1_stderr": 0.01505186948671501, "mc2": 0.42431454034377986, "mc2_stderr": 0.015119647586282134 }, "headqa_en": { "acc": 0.2567469000729395, "acc_stderr": 0.008343849291869198, "acc_norm": 0.29576951130561635, "acc_norm_stderr": 0.008717251898361426 }, "headqa_es": { "acc": 0.23960612691466082, "acc_stderr": 0.008152930613263032, "acc_norm": 0.27169948942377825, "acc_norm_stderr": 0.00849660053640109 }, "squad2": { "exact": 0.4295460288048513, "f1": 1.8591225589833205, "HasAns_exact": 0.7591093117408907, "HasAns_f1": 3.622362034886802, "NoAns_exact": 0.10092514718250631, "NoAns_f1": 0.10092514718250631, "best_exact": 50.07159100480081, "best_f1": 50.07159100480081 } }, "versions": { "logiqa": 0, "webqs": 0, "triviaqa": 1, "truthfulqa_mc": 1, "headqa_en": 0, "headqa_es": 0, "squad2": 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": {} } }