{ "results": { "anli_r1": { "acc": 0.33, "acc_stderr": 0.014876872027456738 }, "anli_r2": { "acc": 0.344, "acc_stderr": 0.015029633724408943 }, "anli_r3": { "acc": 0.3616666666666667, "acc_stderr": 0.013876131663123877 }, "cb": { "acc": 0.25, "acc_stderr": 0.058387420812114225, "f1": 0.1693693693693694 }, "copa": { "acc": 0.83, "acc_stderr": 0.03775251680686371 }, "hellaswag": { "acc": 0.5343557060346544, "acc_stderr": 0.004977988452502641, "acc_norm": 0.7091216889065923, "acc_norm_stderr": 0.004532393111248685 }, "rte": { "acc": 0.5667870036101083, "acc_stderr": 0.02982676408213827 }, "winogrande": { "acc": 0.6250986582478295, "acc_stderr": 0.013605544523788008 }, "storycloze_2016": { "acc": 0.7573490112239444, "acc_stderr": 0.009913300265342059 }, "boolq": { "acc": 0.6351681957186545, "acc_stderr": 0.008419440984963646 }, "arc_easy": { "acc": 0.6654040404040404, "acc_stderr": 0.009682137724327907, "acc_norm": 0.5997474747474747, "acc_norm_stderr": 0.010053550119896138 }, "arc_challenge": { "acc": 0.3250853242320819, "acc_stderr": 0.013688147309729119, "acc_norm": 0.34215017064846415, "acc_norm_stderr": 0.013864152159177275 }, "sciq": { "acc": 0.894, "acc_stderr": 0.009739551265785138, "acc_norm": 0.822, "acc_norm_stderr": 0.012102167676183589 }, "piqa": { "acc": 0.7676822633297062, "acc_stderr": 0.009853201384168241, "acc_norm": 0.7823721436343852, "acc_norm_stderr": 0.00962740747484087 } }, "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 } }