{ "results": { "anli_r1": { "acc": 0.328, "acc_stderr": 0.014853842487270334 }, "anli_r2": { "acc": 0.337, "acc_stderr": 0.014955087918653605 }, "anli_r3": { "acc": 0.32416666666666666, "acc_stderr": 0.013517438120881624 }, "cb": { "acc": 0.26785714285714285, "acc_stderr": 0.05971290310957636, "f1": 0.18656056587091072 }, "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909283 }, "hellaswag": { "acc": 0.4547898824935272, "acc_stderr": 0.004969341773423513, "acc_norm": 0.5937064329814777, "acc_norm_stderr": 0.004901368629533419 }, "rte": { "acc": 0.5595667870036101, "acc_stderr": 0.029882123363118726 }, "winogrande": { "acc": 0.5769534333070244, "acc_stderr": 0.01388505535905647 }, "storycloze_2016": { "acc": 0.694815606627472, "acc_stderr": 0.010648664383985661 }, "boolq": { "acc": 0.6256880733944954, "acc_stderr": 0.00846424665644323 }, "arc_easy": { "acc": 0.40614478114478114, "acc_stderr": 0.010077409815364048, "acc_norm": 0.3766835016835017, "acc_norm_stderr": 0.009942848077476172 }, "arc_challenge": { "acc": 0.20648464163822525, "acc_stderr": 0.011828865619002316, "acc_norm": 0.2551194539249147, "acc_norm_stderr": 0.012739038695202109 }, "sciq": { "acc": 0.775, "acc_stderr": 0.013211720158614756, "acc_norm": 0.709, "acc_norm_stderr": 0.014370995982377933 }, "piqa": { "acc": 0.6561479869423286, "acc_stderr": 0.011082356277961393, "acc_norm": 0.6528835690968444, "acc_norm_stderr": 0.011107104993128086 } }, "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 } }