{ "results": { "anli_r1": { "acc": 0.352, "acc_stderr": 0.015110404505648677 }, "anli_r2": { "acc": 0.343, "acc_stderr": 0.015019206922356953 }, "anli_r3": { "acc": 0.3425, "acc_stderr": 0.013704669762934722 }, "cb": { "acc": 0.5357142857142857, "acc_stderr": 0.06724777654937658, "f1": 0.30043290043290044 }, "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909282 }, "hellaswag": { "acc": 0.4446325433180641, "acc_stderr": 0.004959094146471523, "acc_norm": 0.589523999203346, "acc_norm_stderr": 0.004909148239488278 }, "rte": { "acc": 0.51985559566787, "acc_stderr": 0.030072723167317177 }, "winogrande": { "acc": 0.56353591160221, "acc_stderr": 0.01393856946567702 }, "storycloze_2016": { "acc": 0.6953500801710315, "acc_stderr": 0.010643426988646806 }, "boolq": { "acc": 0.5825688073394495, "acc_stderr": 0.00862499005021668 }, "arc_easy": { "acc": 0.5913299663299664, "acc_stderr": 0.010087174498762883, "acc_norm": 0.5627104377104377, "acc_norm_stderr": 0.010178768429321595 }, "arc_challenge": { "acc": 0.2696245733788396, "acc_stderr": 0.01296804068686915, "acc_norm": 0.2986348122866894, "acc_norm_stderr": 0.013374078615068756 }, "sciq": { "acc": 0.874, "acc_stderr": 0.010499249222408046, "acc_norm": 0.843, "acc_norm_stderr": 0.01151014697923019 }, "piqa": { "acc": 0.7285092491838956, "acc_stderr": 0.010376251176596135, "acc_norm": 0.7399347116430903, "acc_norm_stderr": 0.010234893249061287 } }, "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 } }