{ "results": { "anli_r1": { "acc": 0.345, "acc_stderr": 0.015039986742055237 }, "anli_r2": { "acc": 0.33, "acc_stderr": 0.014876872027456724 }, "anli_r3": { "acc": 0.32666666666666666, "acc_stderr": 0.013544340907003665 }, "cb": { "acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.30501089324618735 }, "copa": { "acc": 0.8, "acc_stderr": 0.040201512610368445 }, "hellaswag": { "acc": 0.4470225054769966, "acc_stderr": 0.004961693567208819, "acc_norm": 0.5973909579764987, "acc_norm_stderr": 0.004894210011303224 }, "rte": { "acc": 0.5415162454873647, "acc_stderr": 0.029992535385373314 }, "winogrande": { "acc": 0.5572217837411207, "acc_stderr": 0.013960157350784983 }, "storycloze_2016": { "acc": 0.6996258685195083, "acc_stderr": 0.010600915927985021 }, "boolq": { "acc": 0.6009174311926605, "acc_stderr": 0.008565077958836783 }, "arc_easy": { "acc": 0.6094276094276094, "acc_stderr": 0.010011059112064237, "acc_norm": 0.5951178451178452, "acc_norm_stderr": 0.0100724239603957 }, "arc_challenge": { "acc": 0.2935153583617747, "acc_stderr": 0.01330725044494112, "acc_norm": 0.318259385665529, "acc_norm_stderr": 0.013611993916971453 }, "sciq": { "acc": 0.907, "acc_stderr": 0.00918887563499668, "acc_norm": 0.886, "acc_norm_stderr": 0.010055103435823332 }, "piqa": { "acc": 0.735038084874864, "acc_stderr": 0.010296557993316047, "acc_norm": 0.7529923830250272, "acc_norm_stderr": 0.01006226814077264 } }, "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 } }