{ "results": { "anli_r1": { "acc": 0.312, "acc_stderr": 0.014658474370509005 }, "anli_r2": { "acc": 0.328, "acc_stderr": 0.014853842487270336 }, "anli_r3": { "acc": 0.32666666666666666, "acc_stderr": 0.013544340907003665 }, "cb": { "acc": 0.5, "acc_stderr": 0.06741998624632421, "f1": 0.4627446995868048 }, "copa": { "acc": 0.71, "acc_stderr": 0.04560480215720684 }, "hellaswag": { "acc": 0.3833897629954192, "acc_stderr": 0.0048521826212742526, "acc_norm": 0.47769368651663013, "acc_norm_stderr": 0.00498481339101621 }, "rte": { "acc": 0.4657039711191336, "acc_stderr": 0.030025579819366426 }, "winogrande": { "acc": 0.5706393054459353, "acc_stderr": 0.01391153749996917 }, "storycloze_2016": { "acc": 0.6456440406199893, "acc_stderr": 0.011061031791615487 }, "boolq": { "acc": 0.5324159021406728, "acc_stderr": 0.008726657178723137 }, "arc_easy": { "acc": 0.6094276094276094, "acc_stderr": 0.01001105911206424, "acc_norm": 0.5631313131313131, "acc_norm_stderr": 0.010177672928157695 }, "arc_challenge": { "acc": 0.2832764505119454, "acc_stderr": 0.013167478735134575, "acc_norm": 0.29436860068259385, "acc_norm_stderr": 0.013318528460539422 }, "sciq": { "acc": 0.84, "acc_stderr": 0.011598902298689004, "acc_norm": 0.795, "acc_norm_stderr": 0.012772554096113118 }, "piqa": { "acc": 0.750816104461371, "acc_stderr": 0.010091882770120216, "acc_norm": 0.7584330794341676, "acc_norm_stderr": 0.009986718001804439 } }, "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 } }