{ "results": { "anli_r1": { "acc": 0.329, "acc_stderr": 0.014865395385928355 }, "anli_r2": { "acc": 0.341, "acc_stderr": 0.014998131348402704 }, "anli_r3": { "acc": 0.325, "acc_stderr": 0.013526454480351028 }, "cb": { "acc": 0.25, "acc_stderr": 0.058387420812114225, "f1": 0.24860681114551084 }, "copa": { "acc": 0.84, "acc_stderr": 0.03684529491774711 }, "hellaswag": { "acc": 0.4788886675960964, "acc_stderr": 0.004985331652408345, "acc_norm": 0.6285600477992431, "acc_norm_stderr": 0.004822022254886021 }, "rte": { "acc": 0.48014440433212996, "acc_stderr": 0.0300727231673172 }, "winogrande": { "acc": 0.590370955011839, "acc_stderr": 0.013821049109655465 }, "storycloze_2016": { "acc": 0.7172634954569749, "acc_stderr": 0.01041380648612127 }, "boolq": { "acc": 0.6146788990825688, "acc_stderr": 0.008511930879680645 }, "arc_easy": { "acc": 0.6380471380471381, "acc_stderr": 0.009860991466688486, "acc_norm": 0.625, "acc_norm_stderr": 0.009933992677987828 }, "arc_challenge": { "acc": 0.29948805460750855, "acc_stderr": 0.013385021637313565, "acc_norm": 0.33276450511945393, "acc_norm_stderr": 0.01376986304619231 }, "sciq": { "acc": 0.916, "acc_stderr": 0.008776162089491122, "acc_norm": 0.9, "acc_norm_stderr": 0.009491579957525049 }, "piqa": { "acc": 0.7584330794341676, "acc_stderr": 0.009986718001804463, "acc_norm": 0.7562568008705114, "acc_norm_stderr": 0.010017199471500609 } }, "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 } }