{ "results": { "anli_r1": { "acc": 0.314, "acc_stderr": 0.01468399195108797 }, "anli_r2": { "acc": 0.332, "acc_stderr": 0.014899597242811478 }, "anli_r3": { "acc": 0.33666666666666667, "acc_stderr": 0.013647602942406401 }, "cb": { "acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.2689474934663815 }, "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909283 }, "hellaswag": { "acc": 0.4790878311093408, "acc_stderr": 0.004985415250690911, "acc_norm": 0.6315475004979088, "acc_norm_stderr": 0.0048139910698082634 }, "rte": { "acc": 0.5703971119133574, "acc_stderr": 0.02979666882912467 }, "winogrande": { "acc": 0.5737963693764798, "acc_stderr": 0.013898585965412338 }, "storycloze_2016": { "acc": 0.7177979690005345, "acc_stderr": 0.010407834479647673 }, "boolq": { "acc": 0.6162079510703364, "acc_stderr": 0.008505584729104973 }, "arc_easy": { "acc": 0.6186868686868687, "acc_stderr": 0.009966542497171016, "acc_norm": 0.5349326599326599, "acc_norm_stderr": 0.010234713052723679 }, "arc_challenge": { "acc": 0.2696245733788396, "acc_stderr": 0.012968040686869142, "acc_norm": 0.30119453924914674, "acc_norm_stderr": 0.013406741767847627 }, "sciq": { "acc": 0.86, "acc_stderr": 0.010978183844357801, "acc_norm": 0.779, "acc_norm_stderr": 0.013127502859696239 }, "piqa": { "acc": 0.7562568008705114, "acc_stderr": 0.010017199471500619, "acc_norm": 0.7600652883569097, "acc_norm_stderr": 0.009963625892809545 } }, "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 } }