{ "results": { "anli_r1": { "acc": 0.314, "acc_stderr": 0.014683991951087966 }, "anli_r2": { "acc": 0.326, "acc_stderr": 0.014830507204541035 }, "anli_r3": { "acc": 0.355, "acc_stderr": 0.013819249004047296 }, "cb": { "acc": 0.32142857142857145, "acc_stderr": 0.06297362289056341, "f1": 0.28889599317988063 }, "copa": { "acc": 0.73, "acc_stderr": 0.044619604333847394 }, "hellaswag": { "acc": 0.4563831905994822, "acc_stderr": 0.004970759774676886, "acc_norm": 0.5928101971718781, "acc_norm_stderr": 0.004903066639761947 }, "rte": { "acc": 0.5956678700361011, "acc_stderr": 0.029540420517619716 }, "winogrande": { "acc": 0.5619573796369376, "acc_stderr": 0.013944181296470804 }, "storycloze_2016": { "acc": 0.6520577231427044, "acc_stderr": 0.011014779784784828 }, "boolq": { "acc": 0.5571865443425077, "acc_stderr": 0.008687668766930832 }, "arc_easy": { "acc": 0.39057239057239057, "acc_stderr": 0.010011059112064236, "acc_norm": 0.36658249158249157, "acc_norm_stderr": 0.009887786585323946 }, "arc_challenge": { "acc": 0.2090443686006826, "acc_stderr": 0.01188274698740645, "acc_norm": 0.25170648464163825, "acc_norm_stderr": 0.012682496334042968 }, "sciq": { "acc": 0.703, "acc_stderr": 0.014456832294801098, "acc_norm": 0.647, "acc_norm_stderr": 0.015120172605483697 }, "piqa": { "acc": 0.6322089227421109, "acc_stderr": 0.011250616646678795, "acc_norm": 0.6311207834602829, "acc_norm_stderr": 0.011257546676908809 } }, "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 } }