{ "results": { "anli_r1": { "acc": 0.311, "acc_stderr": 0.014645596385722692 }, "anli_r2": { "acc": 0.357, "acc_stderr": 0.015158521721486773 }, "anli_r3": { "acc": 0.3233333333333333, "acc_stderr": 0.01350837286730022 }, "cb": { "acc": 0.5178571428571429, "acc_stderr": 0.06737697508644647, "f1": 0.4390740542278427 }, "copa": { "acc": 0.75, "acc_stderr": 0.04351941398892446 }, "hellaswag": { "acc": 0.4457279426409082, "acc_stderr": 0.004960299952519407, "acc_norm": 0.5819557857000598, "acc_norm_stderr": 0.004922294797766662 }, "rte": { "acc": 0.5884476534296029, "acc_stderr": 0.029621832222417196 }, "winogrande": { "acc": 0.5367008681925809, "acc_stderr": 0.01401457845884326 }, "storycloze_2016": { "acc": 0.6926777124532336, "acc_stderr": 0.010669445081866662 }, "boolq": { "acc": 0.5776758409785933, "acc_stderr": 0.008638883260317736 }, "arc_easy": { "acc": 0.5925925925925926, "acc_stderr": 0.010082326627832865, "acc_norm": 0.5656565656565656, "acc_norm_stderr": 0.010170943451269421 }, "arc_challenge": { "acc": 0.2645051194539249, "acc_stderr": 0.012889272949313366, "acc_norm": 0.2883959044368601, "acc_norm_stderr": 0.01323839442242817 }, "sciq": { "acc": 0.863, "acc_stderr": 0.010878848714333316, "acc_norm": 0.821, "acc_norm_stderr": 0.012128730605719113 }, "piqa": { "acc": 0.7328618063112078, "acc_stderr": 0.010323440492612445, "acc_norm": 0.7437431991294886, "acc_norm_stderr": 0.010185787831565058 } }, "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 } }