{ "results": { "anli_r1": { "acc": 0.309, "acc_stderr": 0.014619600977206491 }, "anli_r2": { "acc": 0.343, "acc_stderr": 0.015019206922356953 }, "anli_r3": { "acc": 0.3333333333333333, "acc_stderr": 0.013613950010225601 }, "cb": { "acc": 0.35714285714285715, "acc_stderr": 0.0646095738380922, "f1": 0.24743230625583568 }, "copa": { "acc": 0.57, "acc_stderr": 0.04975698519562428 }, "hellaswag": { "acc": 0.2835092611033659, "acc_stderr": 0.004497803024345142, "acc_norm": 0.2983469428400717, "acc_norm_stderr": 0.004565974937793714 }, "rte": { "acc": 0.516245487364621, "acc_stderr": 0.030080573208738064 }, "winogrande": { "acc": 0.5011838989739542, "acc_stderr": 0.014052446290529015 }, "storycloze_2016": { "acc": 0.5628006413682523, "acc_stderr": 0.011470867061664471 }, "boolq": { "acc": 0.4938837920489297, "acc_stderr": 0.00874440068189347 }, "arc_easy": { "acc": 0.3888888888888889, "acc_stderr": 0.01000324833531376, "acc_norm": 0.36237373737373735, "acc_norm_stderr": 0.009863468202583789 }, "arc_challenge": { "acc": 0.19112627986348124, "acc_stderr": 0.011490055292778592, "acc_norm": 0.2167235494880546, "acc_norm_stderr": 0.012040156713481189 }, "sciq": { "acc": 0.672, "acc_stderr": 0.014853842487270334, "acc_norm": 0.627, "acc_norm_stderr": 0.015300493622922814 }, "piqa": { "acc": 0.6251360174102285, "acc_stderr": 0.011294565805619017, "acc_norm": 0.6218715995647442, "acc_norm_stderr": 0.011313980666854535 } }, "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 } }