{ "results": { "anli_r1": { "acc": 0.33, "acc_stderr": 0.014876872027456729 }, "anli_r2": { "acc": 0.329, "acc_stderr": 0.014865395385928355 }, "anli_r3": { "acc": 0.33166666666666667, "acc_stderr": 0.013596836729485171 }, "cb": { "acc": 0.19642857142857142, "acc_stderr": 0.05357142857142859, "f1": 0.19293024227234748 }, "copa": { "acc": 0.76, "acc_stderr": 0.04292346959909283 }, "hellaswag": { "acc": 0.4727145986855208, "acc_stderr": 0.004982346155911131, "acc_norm": 0.6357299342760406, "acc_norm_stderr": 0.0048024139199326545 }, "rte": { "acc": 0.5379061371841155, "acc_stderr": 0.030009848912529113 }, "winogrande": { "acc": 0.5974743488555643, "acc_stderr": 0.013782866831703044 }, "storycloze_2016": { "acc": 0.7231427044361304, "acc_stderr": 0.01034711289027693 }, "boolq": { "acc": 0.6321100917431193, "acc_stderr": 0.008434276591093021 }, "arc_easy": { "acc": 0.6325757575757576, "acc_stderr": 0.009892552616211555, "acc_norm": 0.617003367003367, "acc_norm_stderr": 0.00997492038453649 }, "arc_challenge": { "acc": 0.32337883959044367, "acc_stderr": 0.013669421630012129, "acc_norm": 0.3199658703071672, "acc_norm_stderr": 0.013631345807016195 }, "sciq": { "acc": 0.91, "acc_stderr": 0.009054390204866439, "acc_norm": 0.898, "acc_norm_stderr": 0.009575368801653873 }, "piqa": { "acc": 0.7453754080522307, "acc_stderr": 0.010164432237060489, "acc_norm": 0.7633297062023939, "acc_norm_stderr": 0.009916841655042809 } }, "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 } }