{ "results": { "anli_r1": { "acc": 0.321, "acc_stderr": 0.014770821817934656 }, "anli_r2": { "acc": 0.333, "acc_stderr": 0.014910846164229859 }, "anli_r3": { "acc": 0.3475, "acc_stderr": 0.013751753243291852 }, "cb": { "acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.269763077644851 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.4523999203345947, "acc_stderr": 0.004967118575905285, "acc_norm": 0.5977892850029874, "acc_norm_stderr": 0.004893418929918259 }, "rte": { "acc": 0.5054151624548736, "acc_stderr": 0.030094698123239966 }, "winogrande": { "acc": 0.5864246250986582, "acc_stderr": 0.013840971763195308 }, "storycloze_2016": { "acc": 0.711918760021379, "acc_stderr": 0.010472537019822575 }, "boolq": { "acc": 0.600611620795107, "acc_stderr": 0.008566178448007833 }, "arc_easy": { "acc": 0.6359427609427609, "acc_stderr": 0.009873293392779118, "acc_norm": 0.6325757575757576, "acc_norm_stderr": 0.00989255261621155 }, "arc_challenge": { "acc": 0.3122866894197952, "acc_stderr": 0.013542598541688064, "acc_norm": 0.33532423208191126, "acc_norm_stderr": 0.013796182947785566 }, "sciq": { "acc": 0.926, "acc_stderr": 0.008282064512704159, "acc_norm": 0.928, "acc_norm_stderr": 0.008178195576218681 }, "piqa": { "acc": 0.750272034820457, "acc_stderr": 0.010099232969867488, "acc_norm": 0.7573449401523396, "acc_norm_stderr": 0.010002002569708688 } }, "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 } }