{ "results": { "anli_r1": { "acc": 0.347, "acc_stderr": 0.015060472031706622 }, "anli_r2": { "acc": 0.346, "acc_stderr": 0.015050266127564448 }, "anli_r3": { "acc": 0.335, "acc_stderr": 0.013630871843821476 }, "cb": { "acc": 0.35714285714285715, "acc_stderr": 0.06460957383809221, "f1": 0.2986564996368918 }, "copa": { "acc": 0.8, "acc_stderr": 0.04020151261036845 }, "hellaswag": { "acc": 0.38259310894244175, "acc_stderr": 0.004850268986903357, "acc_norm": 0.48078072097191793, "acc_norm_stderr": 0.004986093791041665 }, "rte": { "acc": 0.5595667870036101, "acc_stderr": 0.029882123363118726 }, "winogrande": { "acc": 0.580110497237569, "acc_stderr": 0.013870943986310396 }, "storycloze_2016": { "acc": 0.6483164083377873, "acc_stderr": 0.011042025772682543 }, "boolq": { "acc": 0.5654434250764526, "acc_stderr": 0.008669824006668013 }, "arc_easy": { "acc": 0.6174242424242424, "acc_stderr": 0.009972837790531477, "acc_norm": 0.6102693602693603, "acc_norm_stderr": 0.010007169391797055 }, "arc_challenge": { "acc": 0.2935153583617747, "acc_stderr": 0.013307250444941122, "acc_norm": 0.31143344709897613, "acc_norm_stderr": 0.013532472099850942 }, "sciq": { "acc": 0.84, "acc_stderr": 0.011598902298689009, "acc_norm": 0.818, "acc_norm_stderr": 0.012207580637662144 }, "piqa": { "acc": 0.7573449401523396, "acc_stderr": 0.010002002569708698, "acc_norm": 0.7665941240478781, "acc_norm_stderr": 0.00986924788952099 } }, "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 } }