{ "results": { "anli_r1": { "acc": 0.337, "acc_stderr": 0.014955087918653605 }, "anli_r2": { "acc": 0.339, "acc_stderr": 0.014976758771620344 }, "anli_r3": { "acc": 0.3308333333333333, "acc_stderr": 0.013588208070708986 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.0663363415035954, "f1": 0.1940928270042194 }, "copa": { "acc": 0.73, "acc_stderr": 0.0446196043338474 }, "hellaswag": { "acc": 0.43706432981477794, "acc_stderr": 0.00495009555596467, "acc_norm": 0.5617406891057558, "acc_norm_stderr": 0.004951594063272048 }, "rte": { "acc": 0.5126353790613718, "acc_stderr": 0.030086851767188564 }, "winogrande": { "acc": 0.5808997632202052, "acc_stderr": 0.013867325192210117 }, "storycloze_2016": { "acc": 0.7076429716729022, "acc_stderr": 0.010518239729787741 }, "boolq": { "acc": 0.6125382262996942, "acc_stderr": 0.00852066653613694 }, "arc_easy": { "acc": 0.5963804713804713, "acc_stderr": 0.010067368960348226, "acc_norm": 0.5340909090909091, "acc_norm_stderr": 0.010235908103438687 }, "arc_challenge": { "acc": 0.2645051194539249, "acc_stderr": 0.012889272949313366, "acc_norm": 0.29180887372013653, "acc_norm_stderr": 0.013284525292403501 }, "sciq": { "acc": 0.827, "acc_stderr": 0.011967214137559933, "acc_norm": 0.751, "acc_norm_stderr": 0.013681600278702301 }, "piqa": { "acc": 0.719804134929271, "acc_stderr": 0.010478122015577082, "acc_norm": 0.720892274211099, "acc_norm_stderr": 0.010465657948498233 } }, "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 } }