{ "results": { "anli_r1": { "acc": 0.306, "acc_stderr": 0.014580006055436967 }, "anli_r2": { "acc": 0.333, "acc_stderr": 0.014910846164229863 }, "anli_r3": { "acc": 0.31916666666666665, "acc_stderr": 0.013462309712005143 }, "cb": { "acc": 0.17857142857142858, "acc_stderr": 0.051642771820087224, "f1": 0.16652752931822698 }, "copa": { "acc": 0.82, "acc_stderr": 0.038612291966536955 }, "hellaswag": { "acc": 0.4774945230033858, "acc_stderr": 0.00498472423511512, "acc_norm": 0.6274646484763992, "acc_norm_stderr": 0.004824917516374197 }, "rte": { "acc": 0.4981949458483754, "acc_stderr": 0.030096267148976633 }, "winogrande": { "acc": 0.6029992107340174, "acc_stderr": 0.013751092519806704 }, "storycloze_2016": { "acc": 0.7156600748262961, "acc_stderr": 0.010431614128665244 }, "boolq": { "acc": 0.6165137614678899, "acc_stderr": 0.008504304838837027 }, "arc_easy": { "acc": 0.6279461279461279, "acc_stderr": 0.009918187193096471, "acc_norm": 0.6069023569023569, "acc_norm_stderr": 0.010022540618945315 }, "arc_challenge": { "acc": 0.3003412969283277, "acc_stderr": 0.013395909309957, "acc_norm": 0.3319112627986348, "acc_norm_stderr": 0.013760988200880536 }, "sciq": { "acc": 0.911, "acc_stderr": 0.009008893392651523, "acc_norm": 0.891, "acc_norm_stderr": 0.00985982840703719 }, "piqa": { "acc": 0.7535364526659413, "acc_stderr": 0.01005481078967182, "acc_norm": 0.7633297062023939, "acc_norm_stderr": 0.009916841655042809 } }, "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 } }