{ "results": { "anli_r1": { "acc": 0.345, "acc_stderr": 0.015039986742055238 }, "anli_r2": { "acc": 0.339, "acc_stderr": 0.014976758771620345 }, "anli_r3": { "acc": 0.3516666666666667, "acc_stderr": 0.013789711695404789 }, "cb": { "acc": 0.2857142857142857, "acc_stderr": 0.060914490387317256, "f1": 0.26703155274583845 }, "copa": { "acc": 0.75, "acc_stderr": 0.04351941398892446 }, "hellaswag": { "acc": 0.3828918542123083, "acc_stderr": 0.004850988215167541, "acc_norm": 0.48605855407289383, "acc_norm_stderr": 0.00498784136740252 }, "rte": { "acc": 0.516245487364621, "acc_stderr": 0.030080573208738064 }, "winogrande": { "acc": 0.55327545382794, "acc_stderr": 0.01397248837161669 }, "storycloze_2016": { "acc": 0.6622127204703367, "acc_stderr": 0.010937034991003881 }, "boolq": { "acc": 0.5700305810397553, "acc_stderr": 0.008658853690729254 }, "arc_easy": { "acc": 0.6393097643097643, "acc_stderr": 0.009853512108416734, "acc_norm": 0.6220538720538721, "acc_norm_stderr": 0.009949405744045481 }, "arc_challenge": { "acc": 0.29692832764505117, "acc_stderr": 0.013352025976725222, "acc_norm": 0.32764505119453924, "acc_norm_stderr": 0.013715847940719346 }, "sciq": { "acc": 0.853, "acc_stderr": 0.011203415395160336, "acc_norm": 0.851, "acc_norm_stderr": 0.01126614068463217 }, "piqa": { "acc": 0.7546245919477693, "acc_stderr": 0.010039831320422396, "acc_norm": 0.76550598476605, "acc_norm_stderr": 0.00988520314324054 } }, "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 } }