{ "results": { "anli_r1": { "acc": 0.318, "acc_stderr": 0.014734079309311901 }, "anli_r2": { "acc": 0.316, "acc_stderr": 0.014709193056057111 }, "anli_r3": { "acc": 0.33416666666666667, "acc_stderr": 0.013622434813136785 }, "cb": { "acc": 0.25, "acc_stderr": 0.058387420812114225, "f1": 0.18062893081761008 }, "copa": { "acc": 0.72, "acc_stderr": 0.04512608598542127 }, "hellaswag": { "acc": 0.39533957379008167, "acc_stderr": 0.0048792428484734605, "acc_norm": 0.49571798446524595, "acc_norm_stderr": 0.004989598426249536 }, "rte": { "acc": 0.51985559566787, "acc_stderr": 0.030072723167317177 }, "winogrande": { "acc": 0.5327545382794001, "acc_stderr": 0.014022300570434132 }, "storycloze_2016": { "acc": 0.6659540352752539, "acc_stderr": 0.010906978048365164 }, "boolq": { "acc": 0.4666666666666667, "acc_stderr": 0.008725599880049204 }, "arc_easy": { "acc": 0.4852693602693603, "acc_stderr": 0.010255329977562098, "acc_norm": 0.45075757575757575, "acc_norm_stderr": 0.010209906101011116 }, "arc_challenge": { "acc": 0.2380546075085324, "acc_stderr": 0.012445770028026208, "acc_norm": 0.2508532423208191, "acc_norm_stderr": 0.012668198621315432 }, "sciq": { "acc": 0.727, "acc_stderr": 0.014095022868717581, "acc_norm": 0.654, "acc_norm_stderr": 0.015050266127564448 }, "piqa": { "acc": 0.70620239390642, "acc_stderr": 0.010627574080514802, "acc_norm": 0.7034820457018498, "acc_norm_stderr": 0.010656078922661133 } }, "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 } }