{ "results": { "anli_r1": { "acc": 0.34, "acc_stderr": 0.014987482264363937 }, "anli_r2": { "acc": 0.375, "acc_stderr": 0.015316971293620996 }, "anli_r3": { "acc": 0.3358333333333333, "acc_stderr": 0.013639261190932882 }, "cb": { "acc": 0.5357142857142857, "acc_stderr": 0.06724777654937658, "f1": 0.538474366304555 }, "copa": { "acc": 0.68, "acc_stderr": 0.046882617226215034 }, "hellaswag": { "acc": 0.3951404102768373, "acc_stderr": 0.004878816961012042, "acc_norm": 0.49372634933280224, "acc_norm_stderr": 0.0049893886134388 }, "rte": { "acc": 0.5090252707581228, "acc_stderr": 0.030091559826331334 }, "winogrande": { "acc": 0.5343330702446725, "acc_stderr": 0.014019317531542569 }, "storycloze_2016": { "acc": 0.6531266702298236, "acc_stderr": 0.011006857922124124 }, "boolq": { "acc": 0.4504587155963303, "acc_stderr": 0.008702022442950874 }, "arc_easy": { "acc": 0.4718013468013468, "acc_stderr": 0.010243454104071792, "acc_norm": 0.4553872053872054, "acc_norm_stderr": 0.010218861787618732 }, "arc_challenge": { "acc": 0.23293515358361774, "acc_stderr": 0.012352507042617394, "acc_norm": 0.26023890784982934, "acc_norm_stderr": 0.012821930225112556 }, "sciq": { "acc": 0.728, "acc_stderr": 0.014078856992462615, "acc_norm": 0.711, "acc_norm_stderr": 0.014341711358296183 }, "piqa": { "acc": 0.6920565832426551, "acc_stderr": 0.010770892367463689, "acc_norm": 0.6985854189336235, "acc_norm_stderr": 0.01070624824275376 } }, "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 } }