{ "results": { "anli_r1": { "acc": 0.365, "acc_stderr": 0.015231776226264891 }, "anli_r2": { "acc": 0.357, "acc_stderr": 0.015158521721486778 }, "anli_r3": { "acc": 0.3458333333333333, "acc_stderr": 0.013736245342311014 }, "cb": { "acc": 0.5357142857142857, "acc_stderr": 0.06724777654937658, "f1": 0.3502178649237473 }, "copa": { "acc": 0.74, "acc_stderr": 0.0440844002276808 }, "hellaswag": { "acc": 0.442441744672376, "acc_stderr": 0.0049566093272184015, "acc_norm": 0.5873332005576578, "acc_norm_stderr": 0.004913076844433741 }, "rte": { "acc": 0.48736462093862815, "acc_stderr": 0.030086851767188564 }, "winogrande": { "acc": 0.5469613259668509, "acc_stderr": 0.013990366632148104 }, "storycloze_2016": { "acc": 0.694815606627472, "acc_stderr": 0.010648664383985668 }, "boolq": { "acc": 0.5761467889908257, "acc_stderr": 0.008643046537505769 }, "arc_easy": { "acc": 0.5925925925925926, "acc_stderr": 0.010082326627832861, "acc_norm": 0.5664983164983165, "acc_norm_stderr": 0.010168640625454101 }, "arc_challenge": { "acc": 0.2525597269624573, "acc_stderr": 0.012696728980207704, "acc_norm": 0.29436860068259385, "acc_norm_stderr": 0.013318528460539422 }, "sciq": { "acc": 0.868, "acc_stderr": 0.010709373963528031, "acc_norm": 0.838, "acc_norm_stderr": 0.01165726777130442 }, "piqa": { "acc": 0.7366702937976061, "acc_stderr": 0.010276185322196764, "acc_norm": 0.7448313384113167, "acc_norm_stderr": 0.01017157159252183 } }, "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 } }