{ "results": { "anli_r1": { "acc": 0.336, "acc_stderr": 0.014944140233795027 }, "anli_r2": { "acc": 0.354, "acc_stderr": 0.015129868238451772 }, "anli_r3": { "acc": 0.3325, "acc_stderr": 0.013605417345710526 }, "cb": { "acc": 0.48214285714285715, "acc_stderr": 0.0673769750864465, "f1": 0.40945083014048533 }, "copa": { "acc": 0.77, "acc_stderr": 0.04229525846816506 }, "hellaswag": { "acc": 0.4340768771161123, "acc_stderr": 0.004946221512145273, "acc_norm": 0.5635331607249552, "acc_norm_stderr": 0.004949335356881862 }, "rte": { "acc": 0.49458483754512633, "acc_stderr": 0.030094698123239966 }, "winogrande": { "acc": 0.5453827940015785, "acc_stderr": 0.013994481027065997 }, "storycloze_2016": { "acc": 0.6905398182789952, "acc_stderr": 0.01068995674518907 }, "boolq": { "acc": 0.6085626911314985, "acc_stderr": 0.008536430524403957 }, "arc_easy": { "acc": 0.5841750841750841, "acc_stderr": 0.010113348244647869, "acc_norm": 0.5614478114478114, "acc_norm_stderr": 0.010182010275471116 }, "arc_challenge": { "acc": 0.27986348122866894, "acc_stderr": 0.013119040897725922, "acc_norm": 0.29692832764505117, "acc_norm_stderr": 0.013352025976725223 }, "sciq": { "acc": 0.888, "acc_stderr": 0.009977753031397234, "acc_norm": 0.869, "acc_norm_stderr": 0.010674874844837952 }, "piqa": { "acc": 0.736126224156692, "acc_stderr": 0.010282996367695562, "acc_norm": 0.7421109902067464, "acc_norm_stderr": 0.010206956662056246 } }, "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 } }