{ "results": { "anli_r1": { "acc": 0.311, "acc_stderr": 0.014645596385722692 }, "anli_r2": { "acc": 0.356, "acc_stderr": 0.015149042659306626 }, "anli_r3": { "acc": 0.3425, "acc_stderr": 0.013704669762934727 }, "cb": { "acc": 0.5535714285714286, "acc_stderr": 0.06703189227942397, "f1": 0.49967511371020135 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.4714200358494324, "acc_stderr": 0.004981623292196191, "acc_norm": 0.6261700856403107, "acc_norm_stderr": 0.004828305041904401 }, "rte": { "acc": 0.5342960288808665, "acc_stderr": 0.03002557981936643 }, "winogrande": { "acc": 0.6006314127861089, "acc_stderr": 0.013764933546717612 }, "storycloze_2016": { "acc": 0.729021913415286, "acc_stderr": 0.010278188399635043 }, "boolq": { "acc": 0.6103975535168196, "acc_stderr": 0.008529228894936293 }, "arc_easy": { "acc": 0.6292087542087542, "acc_stderr": 0.009911292822056921, "acc_norm": 0.6153198653198653, "acc_norm_stderr": 0.009983171707008999 }, "arc_challenge": { "acc": 0.2960750853242321, "acc_stderr": 0.013340916085246258, "acc_norm": 0.3122866894197952, "acc_norm_stderr": 0.013542598541688065 }, "sciq": { "acc": 0.911, "acc_stderr": 0.009008893392651535, "acc_norm": 0.892, "acc_norm_stderr": 0.009820001651345693 }, "piqa": { "acc": 0.7578890097932536, "acc_stderr": 0.009994371269104376, "acc_norm": 0.764417845484222, "acc_norm_stderr": 0.009901067586473886 } }, "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 } }