{ "results": { "openbookqa": { "acc": 0.254, "acc_stderr": 0.019486596801643385, "acc_norm": 0.358, "acc_norm_stderr": 0.02146143486285912 }, "winogrande": { "acc": 0.5785319652722968, "acc_stderr": 0.0138780723774976 }, "arc_easy": { "acc": 0.6237373737373737, "acc_stderr": 0.009940646221513789, "acc_norm": 0.5862794612794613, "acc_norm_stderr": 0.010105878530238135 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "mc_taco": { "em": 0.13813813813813813, "f1": 0.479152974631639 }, "wsc273": { "acc": 0.7582417582417582, "acc_stderr": 0.02596031999685269 }, "hellaswag": { "acc": 0.45688109938259314, "acc_stderr": 0.004971192387202445, "acc_norm": 0.6123282214698267, "acc_norm_stderr": 0.004862232790041574 }, "boolq": { "acc": 0.6018348623853211, "acc_stderr": 0.008561755594317445 }, "swag": { "acc": 0.505148455463361, "acc_stderr": 0.003534904635576977, "acc_norm": 0.692292312306308, "acc_norm_stderr": 0.003263207195550976 }, "piqa": { "acc": 0.7393906420021763, "acc_stderr": 0.010241826155811627, "acc_norm": 0.749183895538629, "acc_norm_stderr": 0.010113869547069046 }, "prost": { "acc": 0.2588599487617421, "acc_stderr": 0.0032000423309913543, "acc_norm": 0.26361016225448336, "acc_norm_stderr": 0.0032189046983713983 }, "arc_challenge": { "acc": 0.28754266211604096, "acc_stderr": 0.013226719056266129, "acc_norm": 0.3191126279863481, "acc_norm_stderr": 0.013621696119173304 } }, "versions": { "openbookqa": 0, "winogrande": 0, "arc_easy": 0, "copa": 0, "mc_taco": 0, "wsc273": 0, "hellaswag": 0, "boolq": 1, "swag": 0, "piqa": 0, "prost": 0, "arc_challenge": 0 }, "config": { "model": "hf-causal-experimental", "model_args": "pretrained=facebook/xglm-7.5B,use_accelerate=True", "num_fewshot": 0, "batch_size": "auto", "device": "cuda:0", "no_cache": true, "limit": null, "bootstrap_iters": 100000, "description_dict": {} } }