{ "results": { "anli_r1": { "acc": 0.334, "acc_stderr": 0.014922019523732963 }, "anli_r2": { "acc": 0.315, "acc_stderr": 0.014696631960792503 }, "anli_r3": { "acc": 0.33416666666666667, "acc_stderr": 0.01362243481313678 }, "cb": { "acc": 0.5535714285714286, "acc_stderr": 0.06703189227942398, "f1": 0.38156331670230453 }, "copa": { "acc": 0.55, "acc_stderr": 0.04999999999999999 }, "hellaswag": { "acc": 0.2811192989444334, "acc_stderr": 0.004486268470666331, "acc_norm": 0.29874526986656047, "acc_norm_stderr": 0.0045677248720572 }, "rte": { "acc": 0.5415162454873647, "acc_stderr": 0.029992535385373314 }, "winogrande": { "acc": 0.489344909234412, "acc_stderr": 0.014049294536290396 }, "storycloze_2016": { "acc": 0.5617316942811331, "acc_stderr": 0.011473969561488145 }, "boolq": { "acc": 0.4957186544342508, "acc_stderr": 0.008744734378208071 }, "arc_easy": { "acc": 0.39057239057239057, "acc_stderr": 0.010011059112064236, "acc_norm": 0.3547979797979798, "acc_norm_stderr": 0.009817629113069697 }, "arc_challenge": { "acc": 0.18600682593856654, "acc_stderr": 0.011370940183266728, "acc_norm": 0.2167235494880546, "acc_norm_stderr": 0.012040156713481192 }, "sciq": { "acc": 0.691, "acc_stderr": 0.014619600977206488, "acc_norm": 0.634, "acc_norm_stderr": 0.015240612726405756 }, "piqa": { "acc": 0.6338411316648531, "acc_stderr": 0.011240106070308453, "acc_norm": 0.6284004352557128, "acc_norm_stderr": 0.011274603006724747 } }, "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 } }