{ "results": { "anli_r1": { "acc": 0.332, "acc_stderr": 0.014899597242811473 }, "anli_r2": { "acc": 0.332, "acc_stderr": 0.01489959724281148 }, "anli_r3": { "acc": 0.3258333333333333, "acc_stderr": 0.013535422043417462 }, "cb": { "acc": 0.48214285714285715, "acc_stderr": 0.0673769750864465, "f1": 0.3268398268398269 }, "copa": { "acc": 0.64, "acc_stderr": 0.04824181513244218 }, "hellaswag": { "acc": 0.3599880501892053, "acc_stderr": 0.004790155370993451, "acc_norm": 0.44911372236606256, "acc_norm_stderr": 0.004963872936857939 }, "rte": { "acc": 0.5126353790613718, "acc_stderr": 0.030086851767188564 }, "winogrande": { "acc": 0.5240726124704025, "acc_stderr": 0.014036189665395134 }, "storycloze_2016": { "acc": 0.6264029930518439, "acc_stderr": 0.011186849693644696 }, "boolq": { "acc": 0.5559633027522936, "acc_stderr": 0.00869010521492079 }, "arc_easy": { "acc": 0.5429292929292929, "acc_stderr": 0.01022189756425605, "acc_norm": 0.5315656565656566, "acc_norm_stderr": 0.010239317603199512 }, "arc_challenge": { "acc": 0.2167235494880546, "acc_stderr": 0.012040156713481189, "acc_norm": 0.2593856655290102, "acc_norm_stderr": 0.012808273573927097 }, "sciq": { "acc": 0.881, "acc_stderr": 0.010244215145336662, "acc_norm": 0.877, "acc_norm_stderr": 0.010391293421849879 }, "piqa": { "acc": 0.6985854189336235, "acc_stderr": 0.01070624824275376, "acc_norm": 0.6969532100108814, "acc_norm_stderr": 0.010722648689531501 } }, "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 } }