{ "results": { "xwinograd_en": { "acc": 0.7909677419354839, "acc_stderr": 0.008434667753827384 }, "xwinograd_pt": { "acc": 0.7034220532319392, "acc_stderr": 0.028218035233491295 }, "xwinograd_jp": { "acc": 0.5662148070907195, "acc_stderr": 0.016011986615263228 }, "xwinograd_fr": { "acc": 0.7108433734939759, "acc_stderr": 0.050066428050419186 }, "xwinograd_zh": { "acc": 0.7361111111111112, "acc_stderr": 0.019651614961528674 }, "xwinograd_ru": { "acc": 0.5365079365079365, "acc_stderr": 0.028141315964997568 } }, "versions": { "xwinograd_en": 0, "xwinograd_pt": 0, "xwinograd_jp": 0, "xwinograd_fr": 0, "xwinograd_zh": 0, "xwinograd_ru": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=bigscience/bloom-3b", "num_fewshot": 0, "batch_size": "auto", "device": "cuda", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }