{ "results": { "anli_r1": { "acc": 0.319, "acc_stderr": 0.014746404865473468 }, "anli_r2": { "acc": 0.347, "acc_stderr": 0.01506047203170662 }, "anli_r3": { "acc": 0.3333333333333333, "acc_stderr": 0.013613950010225594 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.0663363415035954, "f1": 0.3536644846617893 }, "copa": { "acc": 0.81, "acc_stderr": 0.03942772444036623 }, "hellaswag": { "acc": 0.4311890061740689, "acc_stderr": 0.0049423027680021055, "acc_norm": 0.5632344154550887, "acc_norm_stderr": 0.004949716368890495 }, "rte": { "acc": 0.5270758122743683, "acc_stderr": 0.030052303463143706 }, "winogrande": { "acc": 0.5461720599842147, "acc_stderr": 0.013992441563707068 }, "storycloze_2016": { "acc": 0.6996258685195083, "acc_stderr": 0.010600915927985028 }, "boolq": { "acc": 0.6045871559633027, "acc_stderr": 0.008551600109082895 }, "arc_easy": { "acc": 0.5883838383838383, "acc_stderr": 0.01009821864671491, "acc_norm": 0.563973063973064, "acc_norm_stderr": 0.010175459582759738 }, "arc_challenge": { "acc": 0.2568259385665529, "acc_stderr": 0.012766923794116801, "acc_norm": 0.2977815699658703, "acc_norm_stderr": 0.013363080107244489 }, "sciq": { "acc": 0.876, "acc_stderr": 0.010427498872343961, "acc_norm": 0.855, "acc_norm_stderr": 0.011139977517890132 }, "piqa": { "acc": 0.7442872687704026, "acc_stderr": 0.010178690109459862, "acc_norm": 0.7524483133841132, "acc_norm_stderr": 0.010069703966857116 } }, "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 } }