{ "results": { "anli_r1": { "acc": 0.337, "acc_stderr": 0.01495508791865361 }, "anli_r2": { "acc": 0.334, "acc_stderr": 0.014922019523732967 }, "anli_r3": { "acc": 0.3466666666666667, "acc_stderr": 0.013744022550571958 }, "cb": { "acc": 0.48214285714285715, "acc_stderr": 0.06737697508644648, "f1": 0.3363636363636364 }, "copa": { "acc": 0.57, "acc_stderr": 0.04975698519562428 }, "hellaswag": { "acc": 0.2824138617805218, "acc_stderr": 0.004492535748097639, "acc_norm": 0.30033857797251545, "acc_norm_stderr": 0.004574683373821047 }, "rte": { "acc": 0.48375451263537905, "acc_stderr": 0.030080573208738064 }, "winogrande": { "acc": 0.47277032359905286, "acc_stderr": 0.014031631629827701 }, "storycloze_2016": { "acc": 0.5611972207375735, "acc_stderr": 0.011475500529062406 }, "boolq": { "acc": 0.4902140672782875, "acc_stderr": 0.008743379884697191 }, "arc_easy": { "acc": 0.3952020202020202, "acc_stderr": 0.010031894052790978, "acc_norm": 0.3661616161616162, "acc_norm_stderr": 0.009885391390947726 }, "arc_challenge": { "acc": 0.19027303754266212, "acc_stderr": 0.0114704241792257, "acc_norm": 0.2090443686006826, "acc_norm_stderr": 0.011882746987406453 }, "sciq": { "acc": 0.69, "acc_stderr": 0.014632638658632902, "acc_norm": 0.635, "acc_norm_stderr": 0.015231776226264902 }, "piqa": { "acc": 0.6273122959738846, "acc_stderr": 0.011281318332897741, "acc_norm": 0.6213275299238302, "acc_norm_stderr": 0.011317163404516852 } }, "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 } }