{ "results": { "anli_r1": { "acc": 0.329, "acc_stderr": 0.014865395385928362 }, "anli_r2": { "acc": 0.335, "acc_stderr": 0.014933117490932568 }, "anli_r3": { "acc": 0.3333333333333333, "acc_stderr": 0.013613950010225606 }, "cb": { "acc": 0.26785714285714285, "acc_stderr": 0.05971290310957635, "f1": 0.24172051976930028 }, "copa": { "acc": 0.79, "acc_stderr": 0.040936018074033256 }, "hellaswag": { "acc": 0.4371639115714001, "acc_stderr": 0.004950221546187576, "acc_norm": 0.5686118303126867, "acc_norm_stderr": 0.004942578520987359 }, "rte": { "acc": 0.5018050541516246, "acc_stderr": 0.030096267148976626 }, "winogrande": { "acc": 0.5651144435674822, "acc_stderr": 0.013932814110418029 }, "storycloze_2016": { "acc": 0.7071084981293426, "acc_stderr": 0.010523873293246304 }, "boolq": { "acc": 0.5165137614678899, "acc_stderr": 0.008740284046486644 }, "arc_easy": { "acc": 0.5778619528619529, "acc_stderr": 0.010134620524592271, "acc_norm": 0.5357744107744108, "acc_norm_stderr": 0.010233488709726544 }, "arc_challenge": { "acc": 0.2645051194539249, "acc_stderr": 0.012889272949313366, "acc_norm": 0.2858361774744027, "acc_norm_stderr": 0.013203196088537367 }, "sciq": { "acc": 0.866, "acc_stderr": 0.010777762298369683, "acc_norm": 0.828, "acc_norm_stderr": 0.011939788882495321 }, "piqa": { "acc": 0.7475516866158868, "acc_stderr": 0.010135665547362364, "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 } }