{ "results": { "anli_r1": { "acc": 0.351, "acc_stderr": 0.015100563798316402 }, "anli_r2": { "acc": 0.352, "acc_stderr": 0.015110404505648668 }, "anli_r3": { "acc": 0.36833333333333335, "acc_stderr": 0.013930121355353778 }, "cb": { "acc": 0.48214285714285715, "acc_stderr": 0.0673769750864465, "f1": 0.3366858237547892 }, "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909283 }, "hellaswag": { "acc": 0.4567815176259709, "acc_stderr": 0.0049711062650465545, "acc_norm": 0.602370045807608, "acc_norm_stderr": 0.004884079750433882 }, "rte": { "acc": 0.5667870036101083, "acc_stderr": 0.02982676408213828 }, "winogrande": { "acc": 0.5595895816890292, "acc_stderr": 0.013952330311915603 }, "storycloze_2016": { "acc": 0.7156600748262961, "acc_stderr": 0.010431614128665242 }, "boolq": { "acc": 0.6070336391437309, "acc_stderr": 0.008542335147970564 }, "arc_easy": { "acc": 0.6456228956228957, "acc_stderr": 0.009815004030251746, "acc_norm": 0.6464646464646465, "acc_norm_stderr": 0.0098097289481515 }, "arc_challenge": { "acc": 0.2986348122866894, "acc_stderr": 0.013374078615068756, "acc_norm": 0.3310580204778157, "acc_norm_stderr": 0.013752062419817836 }, "sciq": { "acc": 0.922, "acc_stderr": 0.008484573530118581, "acc_norm": 0.929, "acc_norm_stderr": 0.008125578442487917 }, "piqa": { "acc": 0.7410228509249184, "acc_stderr": 0.010220966031405609, "acc_norm": 0.7431991294885746, "acc_norm_stderr": 0.010192864802278042 } }, "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 } }