{ "results": { "anli_r1": { "acc": 0.33, "acc_stderr": 0.014876872027456729 }, "anli_r2": { "acc": 0.323, "acc_stderr": 0.014794927843348639 }, "anli_r3": { "acc": 0.3375, "acc_stderr": 0.013655897185463653 }, "cb": { "acc": 0.5178571428571429, "acc_stderr": 0.06737697508644647, "f1": 0.33534439416792355 }, "copa": { "acc": 0.68, "acc_stderr": 0.046882617226215034 }, "hellaswag": { "acc": 0.3972316271659032, "acc_stderr": 0.004883246579496658, "acc_norm": 0.48028281218880703, "acc_norm_stderr": 0.004985900172317692 }, "rte": { "acc": 0.4548736462093863, "acc_stderr": 0.029973636495415252 }, "winogrande": { "acc": 0.494869771112865, "acc_stderr": 0.014051745961790513 }, "storycloze_2016": { "acc": 0.6376269374665954, "acc_stderr": 0.011115793699210296 }, "boolq": { "acc": 0.5314984709480123, "acc_stderr": 0.00872768484861531 }, "arc_easy": { "acc": 0.49284511784511786, "acc_stderr": 0.010258733022446368, "acc_norm": 0.4823232323232323, "acc_norm_stderr": 0.01025336980569897 }, "arc_challenge": { "acc": 0.2354948805460751, "acc_stderr": 0.012399451855004748, "acc_norm": 0.257679180887372, "acc_norm_stderr": 0.012780770562768409 }, "sciq": { "acc": 0.743, "acc_stderr": 0.013825416526895033, "acc_norm": 0.71, "acc_norm_stderr": 0.014356395999905684 }, "piqa": { "acc": 0.6877040261153428, "acc_stderr": 0.010812581599154424, "acc_norm": 0.6964091403699674, "acc_norm_stderr": 0.010728079893076364 } }, "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 } }