{ "results": { "anli_r1": { "acc": 0.317, "acc_stderr": 0.014721675438880222 }, "anli_r2": { "acc": 0.324, "acc_stderr": 0.014806864733738857 }, "anli_r3": { "acc": 0.32, "acc_stderr": 0.013471620929769137 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.0663363415035954, "f1": 0.36560846560846566 }, "copa": { "acc": 0.65, "acc_stderr": 0.04793724854411019 }, "hellaswag": { "acc": 0.3948416650069707, "acc_stderr": 0.004878176541703575, "acc_norm": 0.49083847839075884, "acc_norm_stderr": 0.0049889437217111995 }, "rte": { "acc": 0.48736462093862815, "acc_stderr": 0.030086851767188564 }, "winogrande": { "acc": 0.5256511444356748, "acc_stderr": 0.014033980956108562 }, "storycloze_2016": { "acc": 0.6563335114911811, "acc_stderr": 0.010982724236255946 }, "boolq": { "acc": 0.4452599388379205, "acc_stderr": 0.008692488322023064 }, "arc_easy": { "acc": 0.492003367003367, "acc_stderr": 0.01025847128984197, "acc_norm": 0.45454545454545453, "acc_norm_stderr": 0.010217299762709435 }, "arc_challenge": { "acc": 0.24488054607508533, "acc_stderr": 0.012566273985131356, "acc_norm": 0.28071672354948807, "acc_norm_stderr": 0.013131238126975586 }, "sciq": { "acc": 0.722, "acc_stderr": 0.014174516461485239, "acc_norm": 0.702, "acc_norm_stderr": 0.014470846741134712 }, "piqa": { "acc": 0.6953210010881393, "acc_stderr": 0.010738889044325161, "acc_norm": 0.6958650707290533, "acc_norm_stderr": 0.010733493335721319 } }, "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 } }