{ "results": { "anli_r1": { "acc": 0.342, "acc_stderr": 0.015008706182121731 }, "anli_r2": { "acc": 0.329, "acc_stderr": 0.014865395385928367 }, "anli_r3": { "acc": 0.32666666666666666, "acc_stderr": 0.013544340907003663 }, "cb": { "acc": 0.5892857142857143, "acc_stderr": 0.0663363415035954, "f1": 0.4120234604105572 }, "copa": { "acc": 0.77, "acc_stderr": 0.04229525846816507 }, "hellaswag": { "acc": 0.4666401115315674, "acc_stderr": 0.004978662946687269, "acc_norm": 0.6238797052380004, "acc_norm_stderr": 0.004834207964061318 }, "rte": { "acc": 0.5018050541516246, "acc_stderr": 0.030096267148976626 }, "winogrande": { "acc": 0.590370955011839, "acc_stderr": 0.013821049109655483 }, "storycloze_2016": { "acc": 0.7242116515232496, "acc_stderr": 0.010334748387645674 }, "boolq": { "acc": 0.6162079510703364, "acc_stderr": 0.008505584729104973 }, "arc_easy": { "acc": 0.6266835016835017, "acc_stderr": 0.00992500914280291, "acc_norm": 0.6153198653198653, "acc_norm_stderr": 0.009983171707009 }, "arc_challenge": { "acc": 0.29180887372013653, "acc_stderr": 0.013284525292403492, "acc_norm": 0.31569965870307165, "acc_norm_stderr": 0.013582571095815291 }, "sciq": { "acc": 0.907, "acc_stderr": 0.00918887563499668, "acc_norm": 0.9, "acc_norm_stderr": 0.00949157995752505 }, "piqa": { "acc": 0.750816104461371, "acc_stderr": 0.010091882770120216, "acc_norm": 0.7611534276387377, "acc_norm_stderr": 0.009948120385337484 } }, "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 } }