{ "results": { "anli_r1": { "acc": 0.338, "acc_stderr": 0.014965960710224473 }, "anli_r2": { "acc": 0.328, "acc_stderr": 0.014853842487270333 }, "anli_r3": { "acc": 0.3425, "acc_stderr": 0.013704669762934728 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.0672477765493766, "f1": 0.26271604938271603 }, "copa": { "acc": 0.8, "acc_stderr": 0.040201512610368445 }, "hellaswag": { "acc": 0.46863174666401114, "acc_stderr": 0.0049799521665955405, "acc_norm": 0.6181039633539136, "acc_norm_stderr": 0.004848583243606704 }, "rte": { "acc": 0.5126353790613718, "acc_stderr": 0.030086851767188564 }, "winogrande": { "acc": 0.5643251775848461, "acc_stderr": 0.013935709739615715 }, "storycloze_2016": { "acc": 0.6958845537145911, "acc_stderr": 0.010638172655194789 }, "boolq": { "acc": 0.6100917431192661, "acc_stderr": 0.00853043797286262 }, "arc_easy": { "acc": 0.5984848484848485, "acc_stderr": 0.010058790020755572, "acc_norm": 0.571969696969697, "acc_norm_stderr": 0.01015294331642626 }, "arc_challenge": { "acc": 0.2815699658703072, "acc_stderr": 0.01314337673500901, "acc_norm": 0.3242320819112628, "acc_norm_stderr": 0.01367881039951882 }, "sciq": { "acc": 0.864, "acc_stderr": 0.010845350230472995, "acc_norm": 0.862, "acc_norm_stderr": 0.01091215263250441 }, "piqa": { "acc": 0.7393906420021763, "acc_stderr": 0.010241826155811627, "acc_norm": 0.7383025027203483, "acc_norm_stderr": 0.010255630772708229 } }, "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 } }