{ "results": { "anli_r1": { "acc": 0.335, "acc_stderr": 0.014933117490932572 }, "anli_r2": { "acc": 0.344, "acc_stderr": 0.015029633724408948 }, "anli_r3": { "acc": 0.36916666666666664, "acc_stderr": 0.01393666834928527 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.06724777654937658, "f1": 0.3255198942180551 }, "copa": { "acc": 0.69, "acc_stderr": 0.04648231987117316 }, "hellaswag": { "acc": 0.45518820952001593, "acc_stderr": 0.004969701081068371, "acc_norm": 0.5893248356901015, "acc_norm_stderr": 0.004909509538525173 }, "rte": { "acc": 0.4729241877256318, "acc_stderr": 0.030052303463143706 }, "winogrande": { "acc": 0.5438042620363063, "acc_stderr": 0.01399845361092433 }, "storycloze_2016": { "acc": 0.6964190272581507, "acc_stderr": 0.010632901358518371 }, "boolq": { "acc": 0.5165137614678899, "acc_stderr": 0.008740284046486645 }, "arc_easy": { "acc": 0.5378787878787878, "acc_stderr": 0.010230299628864799, "acc_norm": 0.5206228956228957, "acc_norm_stderr": 0.010251052755716122 }, "arc_challenge": { "acc": 0.26535836177474403, "acc_stderr": 0.012902554762313967, "acc_norm": 0.3037542662116041, "acc_norm_stderr": 0.01343890918477876 }, "sciq": { "acc": 0.806, "acc_stderr": 0.012510816141264362, "acc_norm": 0.777, "acc_norm_stderr": 0.013169830843425672 }, "piqa": { "acc": 0.719804134929271, "acc_stderr": 0.01047812201557708, "acc_norm": 0.7274211099020674, "acc_norm_stderr": 0.010389256803296018 } }, "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 } }