{ "results": { "anli_r1": { "acc": 0.326, "acc_stderr": 0.014830507204541047 }, "anli_r2": { "acc": 0.356, "acc_stderr": 0.015149042659306628 }, "anli_r3": { "acc": 0.335, "acc_stderr": 0.013630871843821474 }, "cb": { "acc": 0.5178571428571429, "acc_stderr": 0.06737697508644648, "f1": 0.43332988160574365 }, "copa": { "acc": 0.71, "acc_stderr": 0.045604802157206845 }, "hellaswag": { "acc": 0.45498904600677154, "acc_stderr": 0.004969521827957945, "acc_norm": 0.5934076877116112, "acc_norm_stderr": 0.004901936511546108 }, "rte": { "acc": 0.48375451263537905, "acc_stderr": 0.030080573208738064 }, "winogrande": { "acc": 0.5580110497237569, "acc_stderr": 0.01395758407910899 }, "storycloze_2016": { "acc": 0.6980224478888295, "acc_stderr": 0.010616985436073357 }, "boolq": { "acc": 0.5954128440366973, "acc_stderr": 0.008584355308932687 }, "arc_easy": { "acc": 0.6073232323232324, "acc_stderr": 0.010020646555538689, "acc_norm": 0.5862794612794613, "acc_norm_stderr": 0.01010587853023813 }, "arc_challenge": { "acc": 0.2713310580204778, "acc_stderr": 0.012993807727545797, "acc_norm": 0.2960750853242321, "acc_norm_stderr": 0.013340916085246263 }, "sciq": { "acc": 0.891, "acc_stderr": 0.00985982840703719, "acc_norm": 0.869, "acc_norm_stderr": 0.010674874844837956 }, "piqa": { "acc": 0.7421109902067464, "acc_stderr": 0.010206956662056257, "acc_norm": 0.749183895538629, "acc_norm_stderr": 0.010113869547069044 } }, "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 } }