{ "results": { "anli_r1": { "acc": 0.328, "acc_stderr": 0.014853842487270334 }, "anli_r2": { "acc": 0.355, "acc_stderr": 0.015139491543780536 }, "anli_r3": { "acc": 0.35083333333333333, "acc_stderr": 0.013782212417178199 }, "cb": { "acc": 0.5, "acc_stderr": 0.06741998624632421, "f1": 0.26794871794871794 }, "copa": { "acc": 0.83, "acc_stderr": 0.037752516806863715 }, "hellaswag": { "acc": 0.4726150169288986, "acc_stderr": 0.004982291744069915, "acc_norm": 0.633240390360486, "acc_norm_stderr": 0.004809352075008949 }, "rte": { "acc": 0.4729241877256318, "acc_stderr": 0.030052303463143706 }, "winogrande": { "acc": 0.5911602209944752, "acc_stderr": 0.013816954295135696 }, "storycloze_2016": { "acc": 0.7279529663281668, "acc_stderr": 0.010290888060871242 }, "boolq": { "acc": 0.6159021406727829, "acc_stderr": 0.008506861063860244 }, "arc_easy": { "acc": 0.6355218855218855, "acc_stderr": 0.00987572928248244, "acc_norm": 0.6111111111111112, "acc_norm_stderr": 0.01000324833531377 }, "arc_challenge": { "acc": 0.2977815699658703, "acc_stderr": 0.013363080107244489, "acc_norm": 0.3046075085324232, "acc_norm_stderr": 0.013449522109932487 }, "sciq": { "acc": 0.915, "acc_stderr": 0.008823426366942324, "acc_norm": 0.917, "acc_norm_stderr": 0.008728527206074787 }, "piqa": { "acc": 0.750272034820457, "acc_stderr": 0.010099232969867486, "acc_norm": 0.7671381936887922, "acc_norm_stderr": 0.009861236071080751 } }, "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 } }