{ "results": { "boolq": { "acc": 0.5700305810397553, "acc_stderr": 0.008658853690729258 }, "hellaswag": { "acc": 0.31099382593108943, "acc_stderr": 0.004619542392006404, "acc_norm": 0.35600477992431784, "acc_norm_stderr": 0.004778380758851136 }, "arc_challenge": { "acc": 0.19539249146757678, "acc_stderr": 0.01158690718995291, "acc_norm": 0.24573378839590443, "acc_norm_stderr": 0.012581033453730107 }, "arc_easy": { "acc": 0.47895622895622897, "acc_stderr": 0.01025069260202259, "acc_norm": 0.43013468013468015, "acc_norm_stderr": 0.010159130445178497 }, "sciq": { "acc": 0.79, "acc_stderr": 0.012886662332274531, "acc_norm": 0.712, "acc_norm_stderr": 0.01432694179723156 } }, "versions": { "boolq": 1, "hellaswag": 0, "arc_challenge": 0, "arc_easy": 0, "sciq": 0 } }