{ "results": { "anli_r1": { "acc": 0.34, "acc_stderr": 0.014987482264363935 }, "anli_r2": { "acc": 0.338, "acc_stderr": 0.014965960710224482 }, "anli_r3": { "acc": 0.35333333333333333, "acc_stderr": 0.013804572162314926 }, "cb": { "acc": 0.44642857142857145, "acc_stderr": 0.06703189227942398, "f1": 0.3011143410852713 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.42202748456482775, "acc_stderr": 0.004928735103635839, "acc_norm": 0.5423222465644294, "acc_norm_stderr": 0.004971874159777697 }, "rte": { "acc": 0.5415162454873647, "acc_stderr": 0.029992535385373314 }, "winogrande": { "acc": 0.5414364640883977, "acc_stderr": 0.014004146853791892 }, "storycloze_2016": { "acc": 0.6766435061464458, "acc_stderr": 0.01081682863306821 }, "boolq": { "acc": 0.5831804281345566, "acc_stderr": 0.008623192108843679 }, "arc_easy": { "acc": 0.5648148148148148, "acc_stderr": 0.01017321643037092, "acc_norm": 0.5349326599326599, "acc_norm_stderr": 0.01023471305272368 }, "arc_challenge": { "acc": 0.257679180887372, "acc_stderr": 0.0127807705627684, "acc_norm": 0.2832764505119454, "acc_norm_stderr": 0.013167478735134576 }, "sciq": { "acc": 0.861, "acc_stderr": 0.010945263761042955, "acc_norm": 0.835, "acc_norm_stderr": 0.01174363286691616 }, "piqa": { "acc": 0.719260065288357, "acc_stderr": 0.010484325438311829, "acc_norm": 0.7263329706202394, "acc_norm_stderr": 0.010402184206229218 } }, "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 } }