{ "results": { "anli_r1": { "acc": 0.333, "acc_stderr": 0.01491084616422986 }, "anli_r2": { "acc": 0.346, "acc_stderr": 0.015050266127564448 }, "anli_r3": { "acc": 0.34833333333333333, "acc_stderr": 0.013759437498874075 }, "cb": { "acc": 0.44642857142857145, "acc_stderr": 0.06703189227942397, "f1": 0.39049382716049386 }, "copa": { "acc": 0.62, "acc_stderr": 0.04878317312145633 }, "hellaswag": { "acc": 0.3990240987851026, "acc_stderr": 0.004886969266944277, "acc_norm": 0.4933280223063135, "acc_norm_stderr": 0.004989337148572078 }, "rte": { "acc": 0.5342960288808665, "acc_stderr": 0.030025579819366422 }, "winogrande": { "acc": 0.505130228887135, "acc_stderr": 0.014051745961790516 }, "storycloze_2016": { "acc": 0.6493853554249065, "acc_stderr": 0.011034317290463294 }, "boolq": { "acc": 0.4434250764525994, "acc_stderr": 0.008688893661318225 }, "arc_easy": { "acc": 0.4823232323232323, "acc_stderr": 0.01025336980569896, "acc_norm": 0.4553872053872054, "acc_norm_stderr": 0.010218861787618725 }, "arc_challenge": { "acc": 0.24573378839590443, "acc_stderr": 0.012581033453730114, "acc_norm": 0.2645051194539249, "acc_norm_stderr": 0.01288927294931337 }, "sciq": { "acc": 0.743, "acc_stderr": 0.013825416526895026, "acc_norm": 0.716, "acc_norm_stderr": 0.01426700906103131 }, "piqa": { "acc": 0.6817192600652884, "acc_stderr": 0.010868093932082235, "acc_norm": 0.6817192600652884, "acc_norm_stderr": 0.010868093932082231 } }, "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 } }