{ "results": { "anli_r1": { "acc": 0.314, "acc_stderr": 0.014683991951087962 }, "anli_r2": { "acc": 0.342, "acc_stderr": 0.015008706182121734 }, "anli_r3": { "acc": 0.32416666666666666, "acc_stderr": 0.013517438120881636 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.0663363415035954, "f1": 0.37437732746529967 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.4823740290778729, "acc_stderr": 0.004986680048438317, "acc_norm": 0.6320454092810197, "acc_norm_stderr": 0.004812633280078256 }, "rte": { "acc": 0.5306859205776173, "acc_stderr": 0.030039730592197812 }, "winogrande": { "acc": 0.5887924230465666, "acc_stderr": 0.013829128358676878 }, "storycloze_2016": { "acc": 0.7215392838054516, "acc_stderr": 0.010365521460604417 }, "boolq": { "acc": 0.599388379204893, "acc_stderr": 0.008570545612096372 }, "arc_easy": { "acc": 0.6342592592592593, "acc_stderr": 0.00988298806941883, "acc_norm": 0.6212121212121212, "acc_norm_stderr": 0.00995373765654204 }, "arc_challenge": { "acc": 0.29180887372013653, "acc_stderr": 0.013284525292403503, "acc_norm": 0.3046075085324232, "acc_norm_stderr": 0.01344952210993249 }, "sciq": { "acc": 0.917, "acc_stderr": 0.00872852720607479, "acc_norm": 0.902, "acc_norm_stderr": 0.009406619184621236 }, "piqa": { "acc": 0.7600652883569097, "acc_stderr": 0.009963625892809544, "acc_norm": 0.7633297062023939, "acc_norm_stderr": 0.009916841655042809 } }, "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 } }