{ "results": { "anli_r1": { "acc": 0.343, "acc_stderr": 0.015019206922356953 }, "anli_r2": { "acc": 0.318, "acc_stderr": 0.014734079309311901 }, "anli_r3": { "acc": 0.325, "acc_stderr": 0.013526454480351028 }, "cb": { "acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.3058470764617691 }, "copa": { "acc": 0.78, "acc_stderr": 0.04163331998932263 }, "hellaswag": { "acc": 0.45727942640908187, "acc_stderr": 0.004971534874389935, "acc_norm": 0.602867954590719, "acc_norm_stderr": 0.004883037758919964 }, "rte": { "acc": 0.48736462093862815, "acc_stderr": 0.030086851767188564 }, "winogrande": { "acc": 0.5808997632202052, "acc_stderr": 0.013867325192210116 }, "storycloze_2016": { "acc": 0.7215392838054516, "acc_stderr": 0.010365521460604415 }, "boolq": { "acc": 0.5489296636085627, "acc_stderr": 0.008703080962379622 }, "arc_easy": { "acc": 0.6325757575757576, "acc_stderr": 0.009892552616211558, "acc_norm": 0.617003367003367, "acc_norm_stderr": 0.009974920384536479 }, "arc_challenge": { "acc": 0.2901023890784983, "acc_stderr": 0.013261573677520759, "acc_norm": 0.31313993174061433, "acc_norm_stderr": 0.013552671543623496 }, "sciq": { "acc": 0.906, "acc_stderr": 0.009233052000787738, "acc_norm": 0.891, "acc_norm_stderr": 0.009859828407037186 }, "piqa": { "acc": 0.7540805223068553, "acc_stderr": 0.010047331865625194, "acc_norm": 0.7698585418933623, "acc_norm_stderr": 0.009820832826839796 } }, "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 } }