{ "results": { "anli_r1": { "acc": 0.326, "acc_stderr": 0.01483050720454105 }, "anli_r2": { "acc": 0.317, "acc_stderr": 0.014721675438880226 }, "anli_r3": { "acc": 0.33416666666666667, "acc_stderr": 0.013622434813136783 }, "cb": { "acc": 0.44642857142857145, "acc_stderr": 0.06703189227942398, "f1": 0.24002574002573998 }, "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909283 }, "hellaswag": { "acc": 0.468034256124278, "acc_stderr": 0.0049795737655758555, "acc_norm": 0.6201951802429795, "acc_norm_stderr": 0.004843462545943488 }, "rte": { "acc": 0.5379061371841155, "acc_stderr": 0.030009848912529113 }, "winogrande": { "acc": 0.5824782951854776, "acc_stderr": 0.013859978264440253 }, "storycloze_2016": { "acc": 0.703901656867985, "acc_stderr": 0.010557307688475116 }, "boolq": { "acc": 0.6162079510703364, "acc_stderr": 0.008505584729104967 }, "arc_easy": { "acc": 0.6035353535353535, "acc_stderr": 0.010037412763064526, "acc_norm": 0.5782828282828283, "acc_norm_stderr": 0.010133255284012327 }, "arc_challenge": { "acc": 0.2815699658703072, "acc_stderr": 0.013143376735009031, "acc_norm": 0.3199658703071672, "acc_norm_stderr": 0.013631345807016191 }, "sciq": { "acc": 0.875, "acc_stderr": 0.010463483381956722, "acc_norm": 0.861, "acc_norm_stderr": 0.010945263761042968 }, "piqa": { "acc": 0.73449401523395, "acc_stderr": 0.010303308653024429, "acc_norm": 0.7459194776931447, "acc_norm_stderr": 0.01015727199913505 } }, "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 } }