{ "results": { "anli_r1": { "acc": 0.334, "acc_stderr": 0.014922019523732961 }, "anli_r2": { "acc": 0.36, "acc_stderr": 0.015186527932040126 }, "anli_r3": { "acc": 0.3475, "acc_stderr": 0.013751753243291854 }, "cb": { "acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.34267399267399273 }, "copa": { "acc": 0.66, "acc_stderr": 0.04760952285695237 }, "hellaswag": { "acc": 0.3934475204142601, "acc_stderr": 0.004875162699121657, "acc_norm": 0.4903405696076479, "acc_norm_stderr": 0.004988850185477487 }, "rte": { "acc": 0.5126353790613718, "acc_stderr": 0.030086851767188564 }, "winogrande": { "acc": 0.5059194948697711, "acc_stderr": 0.014051500838485807 }, "storycloze_2016": { "acc": 0.6520577231427044, "acc_stderr": 0.011014779784784831 }, "boolq": { "acc": 0.4529051987767584, "acc_stderr": 0.008706176885837736 }, "arc_easy": { "acc": 0.4877946127946128, "acc_stderr": 0.010256726235129018, "acc_norm": 0.46085858585858586, "acc_norm_stderr": 0.010228298200766124 }, "arc_challenge": { "acc": 0.23208191126279865, "acc_stderr": 0.012336718284948854, "acc_norm": 0.25597269624573377, "acc_norm_stderr": 0.012753013241244514 }, "sciq": { "acc": 0.741, "acc_stderr": 0.01386041525752791, "acc_norm": 0.712, "acc_norm_stderr": 0.01432694179723156 }, "piqa": { "acc": 0.6964091403699674, "acc_stderr": 0.010728079893076364, "acc_norm": 0.7023939064200218, "acc_norm_stderr": 0.01066735379238821 } }, "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 } }