{ "results": { "anli_r1": { "acc": 0.319, "acc_stderr": 0.014746404865473472 }, "anli_r2": { "acc": 0.341, "acc_stderr": 0.014998131348402704 }, "anli_r3": { "acc": 0.3566666666666667, "acc_stderr": 0.013833742805050722 }, "cb": { "acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.224400871459695 }, "copa": { "acc": 0.83, "acc_stderr": 0.03775251680686371 }, "hellaswag": { "acc": 0.4819757020513842, "acc_stderr": 0.004986538243846636, "acc_norm": 0.6331408086038638, "acc_norm_stderr": 0.004809626723626843 }, "rte": { "acc": 0.5631768953068592, "acc_stderr": 0.029855247390314945 }, "winogrande": { "acc": 0.6045777426992897, "acc_stderr": 0.013741678387545347 }, "storycloze_2016": { "acc": 0.7279529663281668, "acc_stderr": 0.010290888060871242 }, "boolq": { "acc": 0.6162079510703364, "acc_stderr": 0.008505584729104983 }, "arc_easy": { "acc": 0.6292087542087542, "acc_stderr": 0.009911292822056923, "acc_norm": 0.6136363636363636, "acc_norm_stderr": 0.009991296778159617 }, "arc_challenge": { "acc": 0.2986348122866894, "acc_stderr": 0.013374078615068756, "acc_norm": 0.3225255972696246, "acc_norm_stderr": 0.013659980894277376 }, "sciq": { "acc": 0.911, "acc_stderr": 0.009008893392651526, "acc_norm": 0.894, "acc_norm_stderr": 0.00973955126578513 }, "piqa": { "acc": 0.7557127312295974, "acc_stderr": 0.010024765172284242, "acc_norm": 0.7682263329706203, "acc_norm_stderr": 0.009845143772794046 } }, "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 } }