{ "results": { "anli_r1": { "acc": 0.357, "acc_stderr": 0.015158521721486773 }, "anli_r2": { "acc": 0.35, "acc_stderr": 0.015090650341444231 }, "anli_r3": { "acc": 0.34833333333333333, "acc_stderr": 0.01375943749887407 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.06724777654937658, "f1": 0.32226930320150665 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.43238398725353516, "acc_stderr": 0.004943945069611458, "acc_norm": 0.5669189404501095, "acc_norm_stderr": 0.004944889545497962 }, "rte": { "acc": 0.5126353790613718, "acc_stderr": 0.030086851767188564 }, "winogrande": { "acc": 0.5493291239147593, "acc_stderr": 0.01398392886904024 }, "storycloze_2016": { "acc": 0.6900053447354356, "acc_stderr": 0.010695042806212555 }, "boolq": { "acc": 0.5951070336391437, "acc_stderr": 0.008585393347962317 }, "arc_easy": { "acc": 0.5909090909090909, "acc_stderr": 0.010088775152615788, "acc_norm": 0.5664983164983165, "acc_norm_stderr": 0.010168640625454103 }, "arc_challenge": { "acc": 0.2687713310580205, "acc_stderr": 0.012955065963710684, "acc_norm": 0.2773037542662116, "acc_norm_stderr": 0.013082095839059374 }, "sciq": { "acc": 0.893, "acc_stderr": 0.009779910359847169, "acc_norm": 0.862, "acc_norm_stderr": 0.010912152632504403 }, "piqa": { "acc": 0.7263329706202394, "acc_stderr": 0.010402184206229211, "acc_norm": 0.733949945593036, "acc_norm_stderr": 0.010310039263352824 } }, "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 } }