{ "results": { "anli_r1": { "acc": 0.343, "acc_stderr": 0.015019206922356953 }, "anli_r2": { "acc": 0.345, "acc_stderr": 0.015039986742055233 }, "anli_r3": { "acc": 0.3525, "acc_stderr": 0.013797164918918359 }, "cb": { "acc": 0.375, "acc_stderr": 0.06527912098338669, "f1": 0.1986111111111111 }, "copa": { "acc": 0.81, "acc_stderr": 0.03942772444036623 }, "hellaswag": { "acc": 0.5324636526588329, "acc_stderr": 0.004979252954977319, "acc_norm": 0.7038438558056164, "acc_norm_stderr": 0.004556276293751941 }, "rte": { "acc": 0.5884476534296029, "acc_stderr": 0.0296218322224172 }, "winogrande": { "acc": 0.6337805840568271, "acc_stderr": 0.0135401443765889 }, "storycloze_2016": { "acc": 0.7573490112239444, "acc_stderr": 0.009913300265342056 }, "boolq": { "acc": 0.6311926605504588, "acc_stderr": 0.008438656079759075 }, "arc_easy": { "acc": 0.6675084175084175, "acc_stderr": 0.009666892606130122, "acc_norm": 0.585016835016835, "acc_norm_stderr": 0.010110383151961139 }, "arc_challenge": { "acc": 0.32081911262798635, "acc_stderr": 0.01364094309194652, "acc_norm": 0.3370307167235495, "acc_norm_stderr": 0.013813476652902267 }, "sciq": { "acc": 0.893, "acc_stderr": 0.009779910359847169, "acc_norm": 0.826, "acc_norm_stderr": 0.011994493230973421 }, "piqa": { "acc": 0.780195865070729, "acc_stderr": 0.009661958616651764, "acc_norm": 0.7894450489662677, "acc_norm_stderr": 0.00951237808123874 } }, "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 } }