{ "results": { "anli_r1": { "acc": 0.345, "acc_stderr": 0.015039986742055235 }, "anli_r2": { "acc": 0.362, "acc_stderr": 0.015204840912919501 }, "anli_r3": { "acc": 0.31583333333333335, "acc_stderr": 0.013424568830356443 }, "cb": { "acc": 0.5, "acc_stderr": 0.06741998624632421, "f1": 0.3176319176319176 }, "copa": { "acc": 0.67, "acc_stderr": 0.04725815626252609 }, "hellaswag": { "acc": 0.376319458275244, "acc_stderr": 0.004834715814208109, "acc_norm": 0.45140410276837284, "acc_norm_stderr": 0.004966158142645416 }, "rte": { "acc": 0.5270758122743683, "acc_stderr": 0.030052303463143706 }, "winogrande": { "acc": 0.489344909234412, "acc_stderr": 0.014049294536290403 }, "storycloze_2016": { "acc": 0.6392303580972741, "acc_stderr": 0.011105110530046359 }, "boolq": { "acc": 0.5064220183486239, "acc_stderr": 0.00874433361394033 }, "arc_easy": { "acc": 0.4739057239057239, "acc_stderr": 0.01024580199024005, "acc_norm": 0.4494949494949495, "acc_norm_stderr": 0.010207308833916035 }, "arc_challenge": { "acc": 0.24744027303754265, "acc_stderr": 0.012610352663292673, "acc_norm": 0.25170648464163825, "acc_norm_stderr": 0.012682496334042963 }, "sciq": { "acc": 0.708, "acc_stderr": 0.014385511563477343, "acc_norm": 0.689, "acc_norm_stderr": 0.014645596385722694 }, "piqa": { "acc": 0.6670293797606094, "acc_stderr": 0.010995648822619067, "acc_norm": 0.676278563656148, "acc_norm_stderr": 0.010916765010708767 } }, "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 } }