{ "results": { "anli_r1": { "acc": 0.325, "acc_stderr": 0.014818724459095524 }, "anli_r2": { "acc": 0.342, "acc_stderr": 0.01500870618212173 }, "anli_r3": { "acc": 0.31666666666666665, "acc_stderr": 0.013434078660827388 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.06724777654937658, "f1": 0.3289760348583877 }, "copa": { "acc": 0.77, "acc_stderr": 0.04229525846816506 }, "hellaswag": { "acc": 0.45160326628161723, "acc_stderr": 0.004966351835028203, "acc_norm": 0.5888269269069907, "acc_norm_stderr": 0.004910409150135493 }, "rte": { "acc": 0.48375451263537905, "acc_stderr": 0.030080573208738064 }, "winogrande": { "acc": 0.5682715074980268, "acc_stderr": 0.01392087211001071 }, "storycloze_2016": { "acc": 0.6953500801710315, "acc_stderr": 0.010643426988646796 }, "boolq": { "acc": 0.608868501529052, "acc_stderr": 0.008535239054221166 }, "arc_easy": { "acc": 0.6342592592592593, "acc_stderr": 0.009882988069418822, "acc_norm": 0.6186868686868687, "acc_norm_stderr": 0.009966542497171021 }, "arc_challenge": { "acc": 0.2909556313993174, "acc_stderr": 0.013273077865907578, "acc_norm": 0.3122866894197952, "acc_norm_stderr": 0.013542598541688067 }, "sciq": { "acc": 0.916, "acc_stderr": 0.008776162089491137, "acc_norm": 0.915, "acc_norm_stderr": 0.008823426366942312 }, "piqa": { "acc": 0.733949945593036, "acc_stderr": 0.010310039263352831, "acc_norm": 0.7486398258977149, "acc_norm_stderr": 0.010121156016819243 } }, "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 } }