{ "results": { "anli_r1": { "acc": 0.317, "acc_stderr": 0.014721675438880224 }, "anli_r2": { "acc": 0.366, "acc_stderr": 0.015240612726405756 }, "anli_r3": { "acc": 0.32083333333333336, "acc_stderr": 0.013480882752851553 }, "cb": { "acc": 0.5, "acc_stderr": 0.06741998624632421, "f1": 0.3491841491841492 }, "copa": { "acc": 0.7, "acc_stderr": 0.046056618647183814 }, "hellaswag": { "acc": 0.36427006572395937, "acc_stderr": 0.004802413919932656, "acc_norm": 0.44503087034455285, "acc_norm_stderr": 0.004959535443170619 }, "rte": { "acc": 0.516245487364621, "acc_stderr": 0.030080573208738064 }, "winogrande": { "acc": 0.5098658247829518, "acc_stderr": 0.014049749833367592 }, "storycloze_2016": { "acc": 0.6435061464457509, "acc_stderr": 0.011075964871051003 }, "boolq": { "acc": 0.5155963302752293, "acc_stderr": 0.008740799550176545 }, "arc_easy": { "acc": 0.5349326599326599, "acc_stderr": 0.010234713052723667, "acc_norm": 0.5193602693602694, "acc_norm_stderr": 0.01025208949116552 }, "arc_challenge": { "acc": 0.23720136518771331, "acc_stderr": 0.012430399829260851, "acc_norm": 0.2696245733788396, "acc_norm_stderr": 0.01296804068686916 }, "sciq": { "acc": 0.899, "acc_stderr": 0.00953361892934099, "acc_norm": 0.887, "acc_norm_stderr": 0.010016552866696865 }, "piqa": { "acc": 0.6936887921653971, "acc_stderr": 0.01075497003236732, "acc_norm": 0.7007616974972797, "acc_norm_stderr": 0.010684130673134581 } }, "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 } }