{ "results": { "anli_r1": { "acc": 0.322, "acc_stderr": 0.014782913600996666 }, "anli_r2": { "acc": 0.357, "acc_stderr": 0.015158521721486774 }, "anli_r3": { "acc": 0.34833333333333333, "acc_stderr": 0.013759437498874079 }, "cb": { "acc": 0.32142857142857145, "acc_stderr": 0.06297362289056341, "f1": 0.2855772439105772 }, "copa": { "acc": 0.77, "acc_stderr": 0.042295258468165044 }, "hellaswag": { "acc": 0.3828918542123083, "acc_stderr": 0.004850988215167546, "acc_norm": 0.4871539533957379, "acc_norm_stderr": 0.004988134303021793 }, "rte": { "acc": 0.4729241877256318, "acc_stderr": 0.030052303463143713 }, "winogrande": { "acc": 0.5722178374112076, "acc_stderr": 0.013905134013839943 }, "storycloze_2016": { "acc": 0.6702298236237306, "acc_stderr": 0.010871682471395135 }, "boolq": { "acc": 0.563914373088685, "acc_stderr": 0.008673312776324932 }, "arc_easy": { "acc": 0.6321548821548821, "acc_stderr": 0.009894923464455193, "acc_norm": 0.61489898989899, "acc_norm_stderr": 0.00998521479873725 }, "arc_challenge": { "acc": 0.2901023890784983, "acc_stderr": 0.01326157367752077, "acc_norm": 0.3250853242320819, "acc_norm_stderr": 0.013688147309729124 }, "sciq": { "acc": 0.85, "acc_stderr": 0.0112972398234093, "acc_norm": 0.842, "acc_norm_stderr": 0.01153989467755957 }, "piqa": { "acc": 0.7600652883569097, "acc_stderr": 0.009963625892809544, "acc_norm": 0.7687704026115343, "acc_norm_stderr": 0.009837063180625334 } }, "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 } }