{ "results": { "anli_r1": { "acc": 0.315, "acc_stderr": 0.014696631960792508 }, "anli_r2": { "acc": 0.341, "acc_stderr": 0.014998131348402699 }, "anli_r3": { "acc": 0.3275, "acc_stderr": 0.013553211167251951 }, "cb": { "acc": 0.5714285714285714, "acc_stderr": 0.06672848092813058, "f1": 0.5046621652657205 }, "copa": { "acc": 0.75, "acc_stderr": 0.04351941398892446 }, "hellaswag": { "acc": 0.3670583549093806, "acc_stderr": 0.004810175357871104, "acc_norm": 0.44682334196375223, "acc_norm_stderr": 0.004961481380023777 }, "rte": { "acc": 0.49097472924187724, "acc_stderr": 0.030091559826331334 }, "winogrande": { "acc": 0.5335438042620363, "acc_stderr": 0.014020826677598101 }, "storycloze_2016": { "acc": 0.6445750935328701, "acc_stderr": 0.01106852845239988 }, "boolq": { "acc": 0.5474006116207951, "acc_stderr": 0.008705669190431184 }, "arc_easy": { "acc": 0.5488215488215489, "acc_stderr": 0.010210757101073475, "acc_norm": 0.5298821548821548, "acc_norm_stderr": 0.010241444322886432 }, "arc_challenge": { "acc": 0.2235494880546075, "acc_stderr": 0.012174896631202607, "acc_norm": 0.257679180887372, "acc_norm_stderr": 0.012780770562768412 }, "sciq": { "acc": 0.875, "acc_stderr": 0.010463483381956722, "acc_norm": 0.875, "acc_norm_stderr": 0.010463483381956722 }, "piqa": { "acc": 0.7002176278563657, "acc_stderr": 0.01068968696713809, "acc_norm": 0.6969532100108814, "acc_norm_stderr": 0.010722648689531501 } }, "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 } }