{ "results": { "anli_r1": { "acc": 0.316, "acc_stderr": 0.014709193056057121 }, "anli_r2": { "acc": 0.324, "acc_stderr": 0.014806864733738856 }, "anli_r3": { "acc": 0.3358333333333333, "acc_stderr": 0.013639261190932887 }, "cb": { "acc": 0.48214285714285715, "acc_stderr": 0.06737697508644648, "f1": 0.3373075012419274 }, "copa": { "acc": 0.75, "acc_stderr": 0.04351941398892446 }, "hellaswag": { "acc": 0.3617805218084047, "acc_stderr": 0.004795337009118191, "acc_norm": 0.44234216291575384, "acc_norm_stderr": 0.0049564940598648966 }, "rte": { "acc": 0.5306859205776173, "acc_stderr": 0.03003973059219781 }, "winogrande": { "acc": 0.5169692186266772, "acc_stderr": 0.014044390401612978 }, "storycloze_2016": { "acc": 0.6221272047033671, "acc_stderr": 0.01121221988713706 }, "boolq": { "acc": 0.55565749235474, "acc_stderr": 0.00869070599067338 }, "arc_easy": { "acc": 0.5429292929292929, "acc_stderr": 0.010221897564256052, "acc_norm": 0.5096801346801347, "acc_norm_stderr": 0.010257860554461127 }, "arc_challenge": { "acc": 0.22440273037542663, "acc_stderr": 0.012191404938603843, "acc_norm": 0.2568259385665529, "acc_norm_stderr": 0.0127669237941168 }, "sciq": { "acc": 0.885, "acc_stderr": 0.010093407594904628, "acc_norm": 0.853, "acc_norm_stderr": 0.011203415395160336 }, "piqa": { "acc": 0.6980413492927094, "acc_stderr": 0.010711732891588357, "acc_norm": 0.691512513601741, "acc_norm_stderr": 0.010776164678037155 } }, "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 } }