{ "results": { "anli_r1": { "acc": 0.348, "acc_stderr": 0.01507060460376841 }, "anli_r2": { "acc": 0.364, "acc_stderr": 0.01522286884052202 }, "anli_r3": { "acc": 0.33666666666666667, "acc_stderr": 0.013647602942406389 }, "cb": { "acc": 0.375, "acc_stderr": 0.06527912098338669, "f1": 0.2536231884057971 }, "copa": { "acc": 0.81, "acc_stderr": 0.03942772444036622 }, "hellaswag": { "acc": 0.4493128858793069, "acc_stderr": 0.0049640758701203404, "acc_norm": 0.5959968133837881, "acc_norm_stderr": 0.0048969523785069215 }, "rte": { "acc": 0.5451263537906137, "acc_stderr": 0.029973636495415252 }, "winogrande": { "acc": 0.5556432517758485, "acc_stderr": 0.013965196769083553 }, "storycloze_2016": { "acc": 0.6990913949759487, "acc_stderr": 0.010606289538707344 }, "boolq": { "acc": 0.6024464831804281, "acc_stderr": 0.008559523256936824 }, "arc_easy": { "acc": 0.6035353535353535, "acc_stderr": 0.010037412763064526, "acc_norm": 0.5854377104377104, "acc_norm_stderr": 0.010108889212447783 }, "arc_challenge": { "acc": 0.2773037542662116, "acc_stderr": 0.013082095839059374, "acc_norm": 0.30887372013651876, "acc_norm_stderr": 0.013501770929344003 }, "sciq": { "acc": 0.902, "acc_stderr": 0.009406619184621236, "acc_norm": 0.882, "acc_norm_stderr": 0.01020686926438179 }, "piqa": { "acc": 0.7383025027203483, "acc_stderr": 0.010255630772708232, "acc_norm": 0.7470076169749728, "acc_norm_stderr": 0.01014288869886245 } }, "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 } }