{ "results": { "anli_r1": { "acc": 0.327, "acc_stderr": 0.014842213153411237 }, "anli_r2": { "acc": 0.322, "acc_stderr": 0.014782913600996667 }, "anli_r3": { "acc": 0.3441666666666667, "acc_stderr": 0.013720551062295756 }, "cb": { "acc": 0.5178571428571429, "acc_stderr": 0.06737697508644647, "f1": 0.4381559220389805 }, "copa": { "acc": 0.78, "acc_stderr": 0.04163331998932263 }, "hellaswag": { "acc": 0.4671380203146783, "acc_stderr": 0.004978992721242829, "acc_norm": 0.6192989444333798, "acc_norm_stderr": 0.004845668799108534 }, "rte": { "acc": 0.5270758122743683, "acc_stderr": 0.030052303463143706 }, "winogrande": { "acc": 0.5872138910812944, "acc_stderr": 0.013837060648682089 }, "storycloze_2016": { "acc": 0.7183324425440941, "acc_stderr": 0.010401844358587667 }, "boolq": { "acc": 0.6107033639143731, "acc_stderr": 0.008528016290984541 }, "arc_easy": { "acc": 0.6287878787878788, "acc_stderr": 0.00991359900184574, "acc_norm": 0.6153198653198653, "acc_norm_stderr": 0.009983171707009008 }, "arc_challenge": { "acc": 0.29180887372013653, "acc_stderr": 0.013284525292403501, "acc_norm": 0.3165529010238908, "acc_norm_stderr": 0.01359243151906808 }, "sciq": { "acc": 0.902, "acc_stderr": 0.009406619184621223, "acc_norm": 0.889, "acc_norm_stderr": 0.009938701010583726 }, "piqa": { "acc": 0.7551686615886833, "acc_stderr": 0.010032309105568798, "acc_norm": 0.7633297062023939, "acc_norm_stderr": 0.009916841655042809 } }, "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 } }