{ "results": { "anli_r1": { "acc": 0.319, "acc_stderr": 0.01474640486547348 }, "anli_r2": { "acc": 0.35, "acc_stderr": 0.015090650341444231 }, "anli_r3": { "acc": 0.3258333333333333, "acc_stderr": 0.013535422043417455 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.06633634150359541, "f1": 0.2796474358974359 }, "copa": { "acc": 0.65, "acc_stderr": 0.047937248544110196 }, "hellaswag": { "acc": 0.3988249352718582, "acc_stderr": 0.0048865590087549884, "acc_norm": 0.4953196574387572, "acc_norm_stderr": 0.004989562798280527 }, "rte": { "acc": 0.5270758122743683, "acc_stderr": 0.030052303463143706 }, "winogrande": { "acc": 0.5185477505919495, "acc_stderr": 0.014042813708888378 }, "storycloze_2016": { "acc": 0.6509887760555852, "acc_stderr": 0.011022640519108546 }, "boolq": { "acc": 0.4437308868501529, "acc_stderr": 0.008689501105367406 }, "arc_easy": { "acc": 0.4781144781144781, "acc_stderr": 0.010249950427234155, "acc_norm": 0.46254208754208753, "acc_norm_stderr": 0.010230952104570805 }, "arc_challenge": { "acc": 0.22184300341296928, "acc_stderr": 0.012141659068147884, "acc_norm": 0.25853242320819114, "acc_norm_stderr": 0.012794553754288684 }, "sciq": { "acc": 0.754, "acc_stderr": 0.013626065817750641, "acc_norm": 0.714, "acc_norm_stderr": 0.014297146862517908 }, "piqa": { "acc": 0.6953210010881393, "acc_stderr": 0.010738889044325161, "acc_norm": 0.7018498367791077, "acc_norm_stderr": 0.010672964114008301 } }, "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 } }