{ "results": { "anli_r1": { "acc": 0.342, "acc_stderr": 0.015008706182121731 }, "anli_r2": { "acc": 0.34, "acc_stderr": 0.014987482264363937 }, "anli_r3": { "acc": 0.3491666666666667, "acc_stderr": 0.013767075395077247 }, "cb": { "acc": 0.42857142857142855, "acc_stderr": 0.06672848092813058, "f1": 0.36394984326018814 }, "copa": { "acc": 0.8, "acc_stderr": 0.040201512610368445 }, "hellaswag": { "acc": 0.47610037841067515, "acc_stderr": 0.004984077906216097, "acc_norm": 0.6333399721171081, "acc_norm_stderr": 0.004809077205343497 }, "rte": { "acc": 0.49097472924187724, "acc_stderr": 0.030091559826331334 }, "winogrande": { "acc": 0.5895816890292028, "acc_stderr": 0.013825107120035866 }, "storycloze_2016": { "acc": 0.721004810261892, "acc_stderr": 0.010371620932652793 }, "boolq": { "acc": 0.6321100917431193, "acc_stderr": 0.008434276591093028 }, "arc_easy": { "acc": 0.6435185185185185, "acc_stderr": 0.009828046544504422, "acc_norm": 0.6165824915824916, "acc_norm_stderr": 0.009976995068264724 }, "arc_challenge": { "acc": 0.3054607508532423, "acc_stderr": 0.013460080478002501, "acc_norm": 0.33361774744027306, "acc_norm_stderr": 0.013778687054176546 }, "sciq": { "acc": 0.916, "acc_stderr": 0.008776162089491123, "acc_norm": 0.905, "acc_norm_stderr": 0.0092769101031033 }, "piqa": { "acc": 0.749183895538629, "acc_stderr": 0.010113869547069044, "acc_norm": 0.7589771490750816, "acc_norm_stderr": 0.009979042717267312 } }, "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 } }