{ "results": { "anli_r1": { "acc": 0.326, "acc_stderr": 0.014830507204541031 }, "anli_r2": { "acc": 0.341, "acc_stderr": 0.014998131348402699 }, "anli_r3": { "acc": 0.345, "acc_stderr": 0.01372842153945488 }, "cb": { "acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.3 }, "copa": { "acc": 0.59, "acc_stderr": 0.04943110704237102 }, "hellaswag": { "acc": 0.28271260705038836, "acc_stderr": 0.004493975527386721, "acc_norm": 0.2983469428400717, "acc_norm_stderr": 0.004565974937793719 }, "rte": { "acc": 0.5270758122743683, "acc_stderr": 0.030052303463143706 }, "winogrande": { "acc": 0.5122336227308603, "acc_stderr": 0.01404827882040562 }, "storycloze_2016": { "acc": 0.5799037947621593, "acc_stderr": 0.011413833983106135 }, "boolq": { "acc": 0.5131498470948013, "acc_stderr": 0.008742030090044975 }, "arc_easy": { "acc": 0.40446127946127947, "acc_stderr": 0.010070746648278785, "acc_norm": 0.3661616161616162, "acc_norm_stderr": 0.009885391390947728 }, "arc_challenge": { "acc": 0.18344709897610922, "acc_stderr": 0.011310170179554541, "acc_norm": 0.22184300341296928, "acc_norm_stderr": 0.012141659068147887 }, "sciq": { "acc": 0.678, "acc_stderr": 0.01478291360099666, "acc_norm": 0.601, "acc_norm_stderr": 0.015493193313162906 }, "piqa": { "acc": 0.6332970620239391, "acc_stderr": 0.01124362501903826, "acc_norm": 0.6240478781284005, "acc_norm_stderr": 0.011301098166895725 } }, "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 } }