{ "results": { "anli_r1": { "acc": 0.33, "acc_stderr": 0.014876872027456736 }, "anli_r2": { "acc": 0.364, "acc_stderr": 0.015222868840522024 }, "anli_r3": { "acc": 0.3616666666666667, "acc_stderr": 0.013876131663123877 }, "cb": { "acc": 0.5535714285714286, "acc_stderr": 0.06703189227942395, "f1": 0.38235294117647056 }, "copa": { "acc": 0.77, "acc_stderr": 0.04229525846816506 }, "hellaswag": { "acc": 0.47321250746863175, "acc_stderr": 0.004982615233057104, "acc_norm": 0.6276638119896435, "acc_norm_stderr": 0.0048243930768266064 }, "rte": { "acc": 0.5956678700361011, "acc_stderr": 0.029540420517619723 }, "winogrande": { "acc": 0.5674822415153907, "acc_stderr": 0.013923911578623814 }, "storycloze_2016": { "acc": 0.7140566541956174, "acc_stderr": 0.010449259851345843 }, "boolq": { "acc": 0.6247706422018349, "acc_stderr": 0.008468397820914277 }, "arc_easy": { "acc": 0.625, "acc_stderr": 0.009933992677987828, "acc_norm": 0.6132154882154882, "acc_norm_stderr": 0.009993308355370966 }, "arc_challenge": { "acc": 0.2815699658703072, "acc_stderr": 0.013143376735009022, "acc_norm": 0.3242320819112628, "acc_norm_stderr": 0.013678810399518822 }, "sciq": { "acc": 0.914, "acc_stderr": 0.008870325962594766, "acc_norm": 0.902, "acc_norm_stderr": 0.009406619184621219 }, "piqa": { "acc": 0.7573449401523396, "acc_stderr": 0.010002002569708698, "acc_norm": 0.7622415669205659, "acc_norm_stderr": 0.009932525779525492 } }, "versions": { "anli_r1": 0, "anli_r2": 0, "anli_r3": 0, "cb": 1, "copa": 0, "hellaswag": 0, "rte": 0, "winogrande": 0, "storycloze_2016": 0, "boolq": 1, "arc_easy": 0, "arc_challenge": 0, "sciq": 0, "piqa": 0 } }