{ "results": { "anli_r1": { "acc": 0.332, "acc_stderr": 0.014899597242811475 }, "anli_r2": { "acc": 0.316, "acc_stderr": 0.014709193056057106 }, "anli_r3": { "acc": 0.31666666666666665, "acc_stderr": 0.013434078660827384 }, "cb": { "acc": 0.30357142857142855, "acc_stderr": 0.06199938655510754, "f1": 0.2503507986266607 }, "copa": { "acc": 0.8, "acc_stderr": 0.040201512610368445 }, "hellaswag": { "acc": 0.4788886675960964, "acc_stderr": 0.004985331652408345, "acc_norm": 0.6412069308902609, "acc_norm_stderr": 0.004786660691181937 }, "rte": { "acc": 0.5740072202166066, "acc_stderr": 0.02976495674177765 }, "winogrande": { "acc": 0.5911602209944752, "acc_stderr": 0.013816954295135684 }, "storycloze_2016": { "acc": 0.7279529663281668, "acc_stderr": 0.010290888060871242 }, "boolq": { "acc": 0.6275229357798165, "acc_stderr": 0.008455846866956086 }, "arc_easy": { "acc": 0.6401515151515151, "acc_stderr": 0.009848484848484846, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.009908978578665755 }, "arc_challenge": { "acc": 0.30887372013651876, "acc_stderr": 0.013501770929344003, "acc_norm": 0.32849829351535836, "acc_norm_stderr": 0.013724978465537377 }, "sciq": { "acc": 0.921, "acc_stderr": 0.008534156773333445, "acc_norm": 0.908, "acc_norm_stderr": 0.00914437639315112 }, "piqa": { "acc": 0.750272034820457, "acc_stderr": 0.010099232969867486, "acc_norm": 0.764961915125136, "acc_norm_stderr": 0.009893146688805312 } }, "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 } }