{ "results": { "anli_r1": { "acc": 0.35, "acc_stderr": 0.01509065034144423 }, "anli_r2": { "acc": 0.346, "acc_stderr": 0.015050266127564448 }, "anli_r3": { "acc": 0.355, "acc_stderr": 0.013819249004047296 }, "cb": { "acc": 0.26785714285714285, "acc_stderr": 0.05971290310957636, "f1": 0.2374338624338624 }, "copa": { "acc": 0.81, "acc_stderr": 0.03942772444036623 }, "hellaswag": { "acc": 0.5215096594303924, "acc_stderr": 0.004985162074336112, "acc_norm": 0.6843258315076678, "acc_norm_stderr": 0.004638339207348913 }, "rte": { "acc": 0.5270758122743683, "acc_stderr": 0.030052303463143706 }, "winogrande": { "acc": 0.5659037095501184, "acc_stderr": 0.013929882555694054 }, "storycloze_2016": { "acc": 0.7455905932656334, "acc_stderr": 0.010071542492663043 }, "boolq": { "acc": 0.6376146788990825, "acc_stderr": 0.008407308655864048 }, "arc_easy": { "acc": 0.6220538720538721, "acc_stderr": 0.009949405744045469, "acc_norm": 0.5395622895622896, "acc_norm_stderr": 0.010227616386289017 }, "arc_challenge": { "acc": 0.29180887372013653, "acc_stderr": 0.013284525292403496, "acc_norm": 0.3216723549488055, "acc_norm_stderr": 0.013650488084494162 }, "sciq": { "acc": 0.87, "acc_stderr": 0.010640169792499361, "acc_norm": 0.807, "acc_norm_stderr": 0.012486268734370145 }, "piqa": { "acc": 0.7627856365614799, "acc_stderr": 0.009924694933586364, "acc_norm": 0.7747551686615887, "acc_norm_stderr": 0.00974664347103214 } }, "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 } }