{ "results": { "anli_r1": { "acc": 0.323, "acc_stderr": 0.01479492784334864 }, "anli_r2": { "acc": 0.302, "acc_stderr": 0.014526080235459548 }, "anli_r3": { "acc": 0.3375, "acc_stderr": 0.013655897185463648 }, "cb": { "acc": 0.48214285714285715, "acc_stderr": 0.0673769750864465, "f1": 0.3081617086193746 }, "copa": { "acc": 0.73, "acc_stderr": 0.044619604333847394 }, "hellaswag": { "acc": 0.45269866560446126, "acc_stderr": 0.004967402792744857, "acc_norm": 0.601274646484764, "acc_norm_stderr": 0.004886353563571844 }, "rte": { "acc": 0.5126353790613718, "acc_stderr": 0.030086851767188564 }, "winogrande": { "acc": 0.569060773480663, "acc_stderr": 0.01391779662333596 }, "storycloze_2016": { "acc": 0.7097808658471406, "acc_stderr": 0.010495529690730063 }, "boolq": { "acc": 0.6223241590214067, "acc_stderr": 0.008479309208281643 }, "arc_easy": { "acc": 0.6456228956228957, "acc_stderr": 0.00981500403025175, "acc_norm": 0.6506734006734006, "acc_norm_stderr": 0.0097828534493993 }, "arc_challenge": { "acc": 0.29180887372013653, "acc_stderr": 0.01328452529240351, "acc_norm": 0.33532423208191126, "acc_norm_stderr": 0.013796182947785562 }, "sciq": { "acc": 0.931, "acc_stderr": 0.00801893405031515, "acc_norm": 0.936, "acc_norm_stderr": 0.007743640226919298 }, "piqa": { "acc": 0.7388465723612623, "acc_stderr": 0.010248738649935581, "acc_norm": 0.7459194776931447, "acc_norm_stderr": 0.010157271999135055 } }, "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 } }