{ "results": { "anli_r1": { "acc": 0.32, "acc_stderr": 0.014758652303574886 }, "anli_r2": { "acc": 0.324, "acc_stderr": 0.014806864733738854 }, "anli_r3": { "acc": 0.3491666666666667, "acc_stderr": 0.01376707539507725 }, "cb": { "acc": 0.5535714285714286, "acc_stderr": 0.06703189227942397, "f1": 0.3890671420083185 }, "copa": { "acc": 0.75, "acc_stderr": 0.04351941398892446 }, "hellaswag": { "acc": 0.4640509858593906, "acc_stderr": 0.0049768677965835555, "acc_norm": 0.6082453694483171, "acc_norm_stderr": 0.004871447106554927 }, "rte": { "acc": 0.5451263537906137, "acc_stderr": 0.029973636495415252 }, "winogrande": { "acc": 0.574585635359116, "acc_stderr": 0.013895257666646378 }, "storycloze_2016": { "acc": 0.711918760021379, "acc_stderr": 0.010472537019822582 }, "boolq": { "acc": 0.5409785932721712, "acc_stderr": 0.008715635308774412 }, "arc_easy": { "acc": 0.6342592592592593, "acc_stderr": 0.009882988069418829, "acc_norm": 0.5837542087542088, "acc_norm_stderr": 0.01011481940450087 }, "arc_challenge": { "acc": 0.2901023890784983, "acc_stderr": 0.013261573677520764, "acc_norm": 0.30119453924914674, "acc_norm_stderr": 0.013406741767847638 }, "sciq": { "acc": 0.896, "acc_stderr": 0.009658016218524301, "acc_norm": 0.88, "acc_norm_stderr": 0.010281328012747386 }, "piqa": { "acc": 0.7551686615886833, "acc_stderr": 0.010032309105568793, "acc_norm": 0.766050054406964, "acc_norm_stderr": 0.009877236895137436 } }, "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 } }