{ "results": { "anli_r1": { "acc": 0.331, "acc_stderr": 0.014888272588203931 }, "anli_r2": { "acc": 0.329, "acc_stderr": 0.014865395385928369 }, "anli_r3": { "acc": 0.3416666666666667, "acc_stderr": 0.013696658778002512 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.0663363415035954, "f1": 0.2951144094001237 }, "copa": { "acc": 0.74, "acc_stderr": 0.04408440022768079 }, "hellaswag": { "acc": 0.4667396932881896, "acc_stderr": 0.0049787293000748915, "acc_norm": 0.6128261302529376, "acc_norm_stderr": 0.004861084534087031 }, "rte": { "acc": 0.5306859205776173, "acc_stderr": 0.030039730592197812 }, "winogrande": { "acc": 0.5895816890292028, "acc_stderr": 0.013825107120035863 }, "storycloze_2016": { "acc": 0.7194013896312133, "acc_stderr": 0.01038980964728882 }, "boolq": { "acc": 0.6073394495412844, "acc_stderr": 0.008541161248702913 }, "arc_easy": { "acc": 0.6292087542087542, "acc_stderr": 0.009911292822056925, "acc_norm": 0.6047979797979798, "acc_norm_stderr": 0.01003189405279098 }, "arc_challenge": { "acc": 0.2909556313993174, "acc_stderr": 0.013273077865907578, "acc_norm": 0.3165529010238908, "acc_norm_stderr": 0.013592431519068079 }, "sciq": { "acc": 0.904, "acc_stderr": 0.009320454434783215, "acc_norm": 0.881, "acc_norm_stderr": 0.010244215145336666 }, "piqa": { "acc": 0.7464635473340587, "acc_stderr": 0.01015009083455179, "acc_norm": 0.7557127312295974, "acc_norm_stderr": 0.01002476517228425 } }, "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 } }