{ "results": { "anli_r1": { "acc": 0.322, "acc_stderr": 0.014782913600996683 }, "anli_r2": { "acc": 0.312, "acc_stderr": 0.014658474370509014 }, "anli_r3": { "acc": 0.31666666666666665, "acc_stderr": 0.01343407866082738 }, "cb": { "acc": 0.5, "acc_stderr": 0.06741998624632421, "f1": 0.3554421768707483 }, "copa": { "acc": 0.71, "acc_stderr": 0.045604802157206845 }, "hellaswag": { "acc": 0.36456881099382593, "acc_stderr": 0.004803253812881047, "acc_norm": 0.4435371439952201, "acc_norm_stderr": 0.004957863944093114 }, "rte": { "acc": 0.5451263537906137, "acc_stderr": 0.029973636495415252 }, "winogrande": { "acc": 0.5280189423835833, "acc_stderr": 0.014030404213405788 }, "storycloze_2016": { "acc": 0.6317477284874399, "acc_stderr": 0.011153823258531741 }, "boolq": { "acc": 0.5749235474006116, "acc_stderr": 0.00864631615937318 }, "arc_easy": { "acc": 0.5328282828282829, "acc_stderr": 0.010237645778853872, "acc_norm": 0.5063131313131313, "acc_norm_stderr": 0.01025896566804444 }, "arc_challenge": { "acc": 0.21928327645051193, "acc_stderr": 0.01209124578761573, "acc_norm": 0.25, "acc_norm_stderr": 0.012653835621466646 }, "sciq": { "acc": 0.862, "acc_stderr": 0.0109121526325044, "acc_norm": 0.848, "acc_norm_stderr": 0.01135891830347529 }, "piqa": { "acc": 0.7007616974972797, "acc_stderr": 0.010684130673134581, "acc_norm": 0.7007616974972797, "acc_norm_stderr": 0.010684130673134581 } }, "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 } }