{ "results": { "anli_r1": { "acc": 0.331, "acc_stderr": 0.014888272588203931 }, "anli_r2": { "acc": 0.342, "acc_stderr": 0.01500870618212173 }, "anli_r3": { "acc": 0.34, "acc_stderr": 0.013680495725767784 }, "cb": { "acc": 0.5357142857142857, "acc_stderr": 0.06724777654937658, "f1": 0.45393112410656267 }, "copa": { "acc": 0.75, "acc_stderr": 0.04351941398892446 }, "hellaswag": { "acc": 0.4833698466440948, "acc_stderr": 0.004987020679861267, "acc_norm": 0.63433578968333, "acc_norm_stderr": 0.004806316342709393 }, "rte": { "acc": 0.5776173285198556, "acc_stderr": 0.029731622646495887 }, "winogrande": { "acc": 0.5864246250986582, "acc_stderr": 0.013840971763195303 }, "storycloze_2016": { "acc": 0.7204703367183325, "acc_stderr": 0.01037770209970486 }, "boolq": { "acc": 0.5253822629969419, "acc_stderr": 0.0087337795418535 }, "arc_easy": { "acc": 0.6224747474747475, "acc_stderr": 0.00994722783346943, "acc_norm": 0.5462962962962963, "acc_norm_stderr": 0.010215708295494117 }, "arc_challenge": { "acc": 0.27986348122866894, "acc_stderr": 0.013119040897725922, "acc_norm": 0.29266211604095566, "acc_norm_stderr": 0.01329591610361942 }, "sciq": { "acc": 0.837, "acc_stderr": 0.011686212712746849, "acc_norm": 0.757, "acc_norm_stderr": 0.013569640199177458 }, "piqa": { "acc": 0.7448313384113167, "acc_stderr": 0.010171571592521822, "acc_norm": 0.76550598476605, "acc_norm_stderr": 0.00988520314324054 } }, "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 } }