{ "results": { "anli_r1": { "acc": 0.324, "acc_stderr": 0.01480686473373886 }, "anli_r2": { "acc": 0.319, "acc_stderr": 0.014746404865473494 }, "anli_r3": { "acc": 0.32166666666666666, "acc_stderr": 0.013490095282989521 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.06633634150359541, "f1": 0.3192955192955193 }, "copa": { "acc": 0.73, "acc_stderr": 0.044619604333847394 }, "hellaswag": { "acc": 0.44015136427006574, "acc_stderr": 0.004953907062096603, "acc_norm": 0.5684126667994424, "acc_norm_stderr": 0.004942853459371548 }, "rte": { "acc": 0.5126353790613718, "acc_stderr": 0.030086851767188564 }, "winogrande": { "acc": 0.5548539857932123, "acc_stderr": 0.01396766295435549 }, "storycloze_2016": { "acc": 0.689470871191876, "acc_stderr": 0.010700112173178448 }, "boolq": { "acc": 0.6024464831804281, "acc_stderr": 0.00855952325693682 }, "arc_easy": { "acc": 0.5824915824915825, "acc_stderr": 0.01011918737777603, "acc_norm": 0.5488215488215489, "acc_norm_stderr": 0.010210757101073468 }, "arc_challenge": { "acc": 0.26791808873720135, "acc_stderr": 0.012942030195136433, "acc_norm": 0.2841296928327645, "acc_norm_stderr": 0.013179442447653886 }, "sciq": { "acc": 0.857, "acc_stderr": 0.011075814808567038, "acc_norm": 0.832, "acc_norm_stderr": 0.01182860583145426 }, "piqa": { "acc": 0.7306855277475517, "acc_stderr": 0.010350004070588758, "acc_norm": 0.7437431991294886, "acc_norm_stderr": 0.010185787831565058 } }, "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 } }