{ "results": { "anli_r1": { "acc": 0.318, "acc_stderr": 0.014734079309311901 }, "anli_r2": { "acc": 0.33, "acc_stderr": 0.01487687202745673 }, "anli_r3": { "acc": 0.32916666666666666, "acc_stderr": 0.01357080625843363 }, "cb": { "acc": 0.4642857142857143, "acc_stderr": 0.0672477765493766, "f1": 0.3314669652855543 }, "copa": { "acc": 0.83, "acc_stderr": 0.03775251680686371 }, "hellaswag": { "acc": 0.4684325831507668, "acc_stderr": 0.0049798268294007665, "acc_norm": 0.6182035451105358, "acc_norm_stderr": 0.004848341560492134 }, "rte": { "acc": 0.5595667870036101, "acc_stderr": 0.02988212336311871 }, "winogrande": { "acc": 0.5698500394632992, "acc_stderr": 0.013914685094716698 }, "storycloze_2016": { "acc": 0.7172634954569749, "acc_stderr": 0.01041380648612127 }, "boolq": { "acc": 0.6024464831804281, "acc_stderr": 0.00855952325693682 }, "arc_easy": { "acc": 0.6136363636363636, "acc_stderr": 0.00999129677815963, "acc_norm": 0.6102693602693603, "acc_norm_stderr": 0.01000716939179705 }, "arc_challenge": { "acc": 0.28668941979522183, "acc_stderr": 0.013214986329274776, "acc_norm": 0.302901023890785, "acc_norm_stderr": 0.013428241573185347 }, "sciq": { "acc": 0.903, "acc_stderr": 0.009363689373248107, "acc_norm": 0.886, "acc_norm_stderr": 0.010055103435823335 }, "piqa": { "acc": 0.749727965179543, "acc_stderr": 0.010106561880089782, "acc_norm": 0.7557127312295974, "acc_norm_stderr": 0.01002476517228425 } }, "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 } }