{ "results": { "anli_r1": { "acc": 0.348, "acc_stderr": 0.015070604603768408 }, "anli_r2": { "acc": 0.36, "acc_stderr": 0.01518652793204012 }, "anli_r3": { "acc": 0.35083333333333333, "acc_stderr": 0.013782212417178195 }, "cb": { "acc": 0.48214285714285715, "acc_stderr": 0.0673769750864465, "f1": 0.40387403446226977 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.4567815176259709, "acc_stderr": 0.004971106265046551, "acc_norm": 0.5992830113523202, "acc_norm_stderr": 0.004890422457747258 }, "rte": { "acc": 0.48375451263537905, "acc_stderr": 0.030080573208738064 }, "winogrande": { "acc": 0.569060773480663, "acc_stderr": 0.013917796623335966 }, "storycloze_2016": { "acc": 0.7247461250668092, "acc_stderr": 0.010328538400500567 }, "boolq": { "acc": 0.5498470948012233, "acc_stderr": 0.008701488203356937 }, "arc_easy": { "acc": 0.6266835016835017, "acc_stderr": 0.009925009142802903, "acc_norm": 0.6203703703703703, "acc_norm_stderr": 0.009958037725468558 }, "arc_challenge": { "acc": 0.2901023890784983, "acc_stderr": 0.013261573677520769, "acc_norm": 0.31143344709897613, "acc_norm_stderr": 0.013532472099850949 }, "sciq": { "acc": 0.923, "acc_stderr": 0.008434580140240632, "acc_norm": 0.903, "acc_norm_stderr": 0.00936368937324812 }, "piqa": { "acc": 0.7578890097932536, "acc_stderr": 0.009994371269104387, "acc_norm": 0.7682263329706203, "acc_norm_stderr": 0.00984514377279405 } }, "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 } }