{ "results": { "anli_r1": { "acc": 0.317, "acc_stderr": 0.01472167543888022 }, "anli_r2": { "acc": 0.328, "acc_stderr": 0.014853842487270334 }, "anli_r3": { "acc": 0.33166666666666667, "acc_stderr": 0.01359683672948517 }, "cb": { "acc": 0.19642857142857142, "acc_stderr": 0.05357142857142859, "f1": 0.1984379958880104 }, "copa": { "acc": 0.82, "acc_stderr": 0.03861229196653697 }, "hellaswag": { "acc": 0.530372435769767, "acc_stderr": 0.004980566907790449, "acc_norm": 0.7078271260705039, "acc_norm_stderr": 0.004538319464111969 }, "rte": { "acc": 0.5884476534296029, "acc_stderr": 0.0296218322224172 }, "winogrande": { "acc": 0.6298342541436464, "acc_stderr": 0.013570454689603911 }, "storycloze_2016": { "acc": 0.757883484767504, "acc_stderr": 0.009905870033193863 }, "boolq": { "acc": 0.6626911314984709, "acc_stderr": 0.008269171495741617 }, "arc_easy": { "acc": 0.680976430976431, "acc_stderr": 0.009564133249441073, "acc_norm": 0.6616161616161617, "acc_norm_stderr": 0.009709034670525096 }, "arc_challenge": { "acc": 0.3310580204778157, "acc_stderr": 0.013752062419817836, "acc_norm": 0.3583617747440273, "acc_norm_stderr": 0.014012883334859871 }, "sciq": { "acc": 0.945, "acc_stderr": 0.007212976294639238, "acc_norm": 0.934, "acc_norm_stderr": 0.007855297938697587 }, "piqa": { "acc": 0.7725788900979326, "acc_stderr": 0.009779850767847239, "acc_norm": 0.7812840043525572, "acc_norm_stderr": 0.009644731932667563 } }, "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 } }