{ "results": { "anli_r1": { "acc": 0.327, "acc_stderr": 0.014842213153411245 }, "anli_r2": { "acc": 0.322, "acc_stderr": 0.014782913600996664 }, "anli_r3": { "acc": 0.345, "acc_stderr": 0.013728421539454878 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.0663363415035954, "f1": 0.2921212121212121 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.4651463851822346, "acc_stderr": 0.004977643730848592, "acc_norm": 0.6108344951204939, "acc_norm_stderr": 0.004865645485910439 }, "rte": { "acc": 0.5812274368231047, "acc_stderr": 0.029696661081234834 }, "winogrande": { "acc": 0.5966850828729282, "acc_stderr": 0.013787257285896248 }, "storycloze_2016": { "acc": 0.7194013896312133, "acc_stderr": 0.01038980964728882 }, "boolq": { "acc": 0.6119266055045871, "acc_stderr": 0.008523130584760836 }, "arc_easy": { "acc": 0.5951178451178452, "acc_stderr": 0.010072423960395703, "acc_norm": 0.5484006734006734, "acc_norm_stderr": 0.010211600726405232 }, "arc_challenge": { "acc": 0.2636518771331058, "acc_stderr": 0.012875929151297046, "acc_norm": 0.3046075085324232, "acc_norm_stderr": 0.013449522109932489 }, "sciq": { "acc": 0.854, "acc_stderr": 0.011171786285496501, "acc_norm": 0.787, "acc_norm_stderr": 0.012953717566737228 }, "piqa": { "acc": 0.750816104461371, "acc_stderr": 0.010091882770120216, "acc_norm": 0.7562568008705114, "acc_norm_stderr": 0.010017199471500609 } }, "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 } }