{ "results": { "anli_r1": { "acc": 0.339, "acc_stderr": 0.014976758771620342 }, "anli_r2": { "acc": 0.353, "acc_stderr": 0.015120172605483692 }, "anli_r3": { "acc": 0.33916666666666667, "acc_stderr": 0.013672343491681819 }, "cb": { "acc": 0.44642857142857145, "acc_stderr": 0.06703189227942398, "f1": 0.2956393200295639 }, "copa": { "acc": 0.7, "acc_stderr": 0.046056618647183814 }, "hellaswag": { "acc": 0.42162915753833896, "acc_stderr": 0.0049281058807760765, "acc_norm": 0.5436168094005178, "acc_norm_stderr": 0.004970759774676884 }, "rte": { "acc": 0.5667870036101083, "acc_stderr": 0.029826764082138274 }, "winogrande": { "acc": 0.5414364640883977, "acc_stderr": 0.014004146853791902 }, "storycloze_2016": { "acc": 0.677712453233565, "acc_stderr": 0.010807461374996361 }, "boolq": { "acc": 0.5957186544342508, "acc_stderr": 0.008583313811372065 }, "arc_easy": { "acc": 0.5669191919191919, "acc_stderr": 0.010167478013701789, "acc_norm": 0.5357744107744108, "acc_norm_stderr": 0.01023348870972654 }, "arc_challenge": { "acc": 0.25853242320819114, "acc_stderr": 0.012794553754288679, "acc_norm": 0.2781569965870307, "acc_norm_stderr": 0.0130944699195388 }, "sciq": { "acc": 0.858, "acc_stderr": 0.011043457699378222, "acc_norm": 0.838, "acc_norm_stderr": 0.011657267771304434 }, "piqa": { "acc": 0.7295973884657236, "acc_stderr": 0.010363167031620792, "acc_norm": 0.7285092491838956, "acc_norm_stderr": 0.010376251176596135 } }, "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 } }