{ "results": { "anli_r1": { "acc": 0.321, "acc_stderr": 0.014770821817934635 }, "anli_r2": { "acc": 0.336, "acc_stderr": 0.014944140233795021 }, "anli_r3": { "acc": 0.3383333333333333, "acc_stderr": 0.013664144006618275 }, "cb": { "acc": 0.5, "acc_stderr": 0.06741998624632421, "f1": 0.34486817325800373 }, "copa": { "acc": 0.54, "acc_stderr": 0.05009082659620332 }, "hellaswag": { "acc": 0.2813184624576778, "acc_stderr": 0.004487235657955673, "acc_norm": 0.2954590718980283, "acc_norm_stderr": 0.004553164013379556 }, "rte": { "acc": 0.5054151624548736, "acc_stderr": 0.030094698123239966 }, "winogrande": { "acc": 0.4956590370955012, "acc_stderr": 0.014051956064076892 }, "storycloze_2016": { "acc": 0.5665419561731694, "acc_stderr": 0.011459581799087402 }, "boolq": { "acc": 0.48623853211009177, "acc_stderr": 0.008741742106878654 }, "arc_easy": { "acc": 0.39225589225589225, "acc_stderr": 0.010018744689650043, "acc_norm": 0.3640572390572391, "acc_norm_stderr": 0.009873293392779117 }, "arc_challenge": { "acc": 0.18088737201365188, "acc_stderr": 0.011248574467407027, "acc_norm": 0.22184300341296928, "acc_norm_stderr": 0.01214165906814789 }, "sciq": { "acc": 0.686, "acc_stderr": 0.014683991951087962, "acc_norm": 0.637, "acc_norm_stderr": 0.015213890444671281 }, "piqa": { "acc": 0.6338411316648531, "acc_stderr": 0.011240106070308455, "acc_norm": 0.6256800870511425, "acc_norm_stderr": 0.01129127680119499 } }, "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 } }