{ "results": { "anli_r1": { "acc": 0.325, "acc_stderr": 0.014818724459095524 }, "anli_r2": { "acc": 0.322, "acc_stderr": 0.014782913600996678 }, "anli_r3": { "acc": 0.335, "acc_stderr": 0.013630871843821476 }, "cb": { "acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.3018475149622691 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.4645488946425015, "acc_stderr": 0.004977223485342027, "acc_norm": 0.6139215295757817, "acc_norm_stderr": 0.004858539527872464 }, "rte": { "acc": 0.5595667870036101, "acc_stderr": 0.029882123363118712 }, "winogrande": { "acc": 0.579321231254933, "acc_stderr": 0.013874526372008327 }, "storycloze_2016": { "acc": 0.721004810261892, "acc_stderr": 0.010371620932652793 }, "boolq": { "acc": 0.5923547400611621, "acc_stderr": 0.008594580270731615 }, "arc_easy": { "acc": 0.6203703703703703, "acc_stderr": 0.009958037725468575, "acc_norm": 0.5959595959595959, "acc_norm_stderr": 0.010069061649549549 }, "arc_challenge": { "acc": 0.2883959044368601, "acc_stderr": 0.013238394422428164, "acc_norm": 0.302901023890785, "acc_norm_stderr": 0.013428241573185349 }, "sciq": { "acc": 0.893, "acc_stderr": 0.009779910359847167, "acc_norm": 0.879, "acc_norm_stderr": 0.010318210380946088 }, "piqa": { "acc": 0.750272034820457, "acc_stderr": 0.010099232969867486, "acc_norm": 0.750816104461371, "acc_norm_stderr": 0.01009188277012021 } }, "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 } }