{ "results": { "anli_r1": { "acc": 0.322, "acc_stderr": 0.014782913600996653 }, "anli_r2": { "acc": 0.349, "acc_stderr": 0.015080663991563098 }, "anli_r3": { "acc": 0.3233333333333333, "acc_stderr": 0.013508372867300219 }, "cb": { "acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.2588235294117647 }, "copa": { "acc": 0.82, "acc_stderr": 0.038612291966536955 }, "hellaswag": { "acc": 0.4731129257120096, "acc_stderr": 0.004982561815214124, "acc_norm": 0.6232822146982673, "acc_norm_stderr": 0.00483572890373141 }, "rte": { "acc": 0.48375451263537905, "acc_stderr": 0.030080573208738064 }, "winogrande": { "acc": 0.5974743488555643, "acc_stderr": 0.01378286683170305 }, "storycloze_2016": { "acc": 0.7172634954569749, "acc_stderr": 0.01041380648612127 }, "boolq": { "acc": 0.6128440366972477, "acc_stderr": 0.008519429207594416 }, "arc_easy": { "acc": 0.6245791245791246, "acc_stderr": 0.0099362185271143, "acc_norm": 0.6052188552188552, "acc_norm_stderr": 0.01003003893588359 }, "arc_challenge": { "acc": 0.29266211604095566, "acc_stderr": 0.01329591610361943, "acc_norm": 0.3302047781569966, "acc_norm_stderr": 0.013743085603760427 }, "sciq": { "acc": 0.914, "acc_stderr": 0.008870325962594766, "acc_norm": 0.889, "acc_norm_stderr": 0.009938701010583726 }, "piqa": { "acc": 0.7453754080522307, "acc_stderr": 0.01016443223706049, "acc_norm": 0.7611534276387377, "acc_norm_stderr": 0.009948120385337484 } }, "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 } }