{ "results": { "anli_r1": { "acc": 0.353, "acc_stderr": 0.015120172605483692 }, "anli_r2": { "acc": 0.315, "acc_stderr": 0.014696631960792503 }, "anli_r3": { "acc": 0.3425, "acc_stderr": 0.013704669762934727 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.06724777654937658, "f1": 0.32716049382716045 }, "copa": { "acc": 0.82, "acc_stderr": 0.038612291966536955 }, "hellaswag": { "acc": 0.46703843855805616, "acc_stderr": 0.004978927164792884, "acc_norm": 0.6155148376817368, "acc_norm_stderr": 0.004854791378657001 }, "rte": { "acc": 0.5740072202166066, "acc_stderr": 0.02976495674177765 }, "winogrande": { "acc": 0.5643251775848461, "acc_stderr": 0.013935709739615713 }, "storycloze_2016": { "acc": 0.7076429716729022, "acc_stderr": 0.01051823972978774 }, "boolq": { "acc": 0.6067278287461774, "acc_stderr": 0.00854350553741787 }, "arc_easy": { "acc": 0.5921717171717171, "acc_stderr": 0.010083950240041214, "acc_norm": 0.5580808080808081, "acc_norm_stderr": 0.010190328123071765 }, "arc_challenge": { "acc": 0.2858361774744027, "acc_stderr": 0.013203196088537369, "acc_norm": 0.29948805460750855, "acc_norm_stderr": 0.013385021637313572 }, "sciq": { "acc": 0.865, "acc_stderr": 0.010811655372416051, "acc_norm": 0.834, "acc_norm_stderr": 0.011772110370812189 }, "piqa": { "acc": 0.749183895538629, "acc_stderr": 0.010113869547069044, "acc_norm": 0.7584330794341676, "acc_norm_stderr": 0.009986718001804448 } }, "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 } }