{ "results": { "anli_r1": { "acc": 0.347, "acc_stderr": 0.015060472031706624 }, "anli_r2": { "acc": 0.325, "acc_stderr": 0.014818724459095527 }, "anli_r3": { "acc": 0.36083333333333334, "acc_stderr": 0.013869180252444864 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.06724777654937658, "f1": 0.2842465753424657 }, "copa": { "acc": 0.62, "acc_stderr": 0.04878317312145632 }, "hellaswag": { "acc": 0.3514240191196973, "acc_stderr": 0.0047643939851110305, "acc_norm": 0.42859988050189207, "acc_norm_stderr": 0.004938643787869535 }, "rte": { "acc": 0.4548736462093863, "acc_stderr": 0.029973636495415252 }, "winogrande": { "acc": 0.5122336227308603, "acc_stderr": 0.01404827882040562 }, "storycloze_2016": { "acc": 0.6264029930518439, "acc_stderr": 0.011186849693644694 }, "boolq": { "acc": 0.5929663608562691, "acc_stderr": 0.008592562887068871 }, "arc_easy": { "acc": 0.5542929292929293, "acc_stderr": 0.01019911818332299, "acc_norm": 0.5223063973063973, "acc_norm_stderr": 0.010249568404555652 }, "arc_challenge": { "acc": 0.257679180887372, "acc_stderr": 0.012780770562768405, "acc_norm": 0.28071672354948807, "acc_norm_stderr": 0.013131238126975574 }, "sciq": { "acc": 0.873, "acc_stderr": 0.010534798620855743, "acc_norm": 0.854, "acc_norm_stderr": 0.011171786285496497 }, "piqa": { "acc": 0.6871599564744287, "acc_stderr": 0.010817714425701104, "acc_norm": 0.6828073993471164, "acc_norm_stderr": 0.01085815545438087 } }, "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 } }