{ "results": { "anli_r1": { "acc": 0.337, "acc_stderr": 0.014955087918653603 }, "anli_r2": { "acc": 0.343, "acc_stderr": 0.015019206922356953 }, "anli_r3": { "acc": 0.3425, "acc_stderr": 0.013704669762934728 }, "cb": { "acc": 0.39285714285714285, "acc_stderr": 0.0658538889806635, "f1": 0.19555555555555557 }, "copa": { "acc": 0.78, "acc_stderr": 0.04163331998932261 }, "hellaswag": { "acc": 0.47868950408285205, "acc_stderr": 0.00498524726030409, "acc_norm": 0.6269667396932882, "acc_norm_stderr": 0.004826224784850451 }, "rte": { "acc": 0.5090252707581228, "acc_stderr": 0.030091559826331334 }, "winogrande": { "acc": 0.585635359116022, "acc_stderr": 0.013844846232268563 }, "storycloze_2016": { "acc": 0.7177979690005345, "acc_stderr": 0.010407834479647672 }, "boolq": { "acc": 0.5525993883792049, "acc_stderr": 0.008696530539281539 }, "arc_easy": { "acc": 0.6102693602693603, "acc_stderr": 0.010007169391797053, "acc_norm": 0.5315656565656566, "acc_norm_stderr": 0.010239317603199509 }, "arc_challenge": { "acc": 0.29436860068259385, "acc_stderr": 0.013318528460539422, "acc_norm": 0.3046075085324232, "acc_norm_stderr": 0.01344952210993249 }, "sciq": { "acc": 0.851, "acc_stderr": 0.011266140684632168, "acc_norm": 0.76, "acc_norm_stderr": 0.013512312258920831 }, "piqa": { "acc": 0.7578890097932536, "acc_stderr": 0.009994371269104387, "acc_norm": 0.7611534276387377, "acc_norm_stderr": 0.009948120385337484 } }, "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 } }