{ "results": { "anli_r1": { "acc": 0.322, "acc_stderr": 0.014782913600996664 }, "anli_r2": { "acc": 0.313, "acc_stderr": 0.014671272822977892 }, "anli_r3": { "acc": 0.3491666666666667, "acc_stderr": 0.013767075395077249 }, "cb": { "acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.2745098039215686 }, "copa": { "acc": 0.75, "acc_stderr": 0.04351941398892446 }, "hellaswag": { "acc": 0.4613622784305915, "acc_stderr": 0.004974860878464439, "acc_norm": 0.6013742282413862, "acc_norm_stderr": 0.004886147907627404 }, "rte": { "acc": 0.5487364620938628, "acc_stderr": 0.029953149241808943 }, "winogrande": { "acc": 0.5509076558800315, "acc_stderr": 0.013979459389140844 }, "storycloze_2016": { "acc": 0.7033671833244255, "acc_stderr": 0.010562819181563226 }, "boolq": { "acc": 0.6174311926605505, "acc_stderr": 0.008500443818876165 }, "arc_easy": { "acc": 0.6022727272727273, "acc_stderr": 0.010042861602178061, "acc_norm": 0.5803872053872053, "acc_norm_stderr": 0.010126315840891539 }, "arc_challenge": { "acc": 0.2832764505119454, "acc_stderr": 0.013167478735134575, "acc_norm": 0.3165529010238908, "acc_norm_stderr": 0.013592431519068079 }, "sciq": { "acc": 0.867, "acc_stderr": 0.010743669132397332, "acc_norm": 0.85, "acc_norm_stderr": 0.011297239823409296 }, "piqa": { "acc": 0.7475516866158868, "acc_stderr": 0.01013566554736236, "acc_norm": 0.7383025027203483, "acc_norm_stderr": 0.010255630772708229 } }, "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 } }