{ "results": { "anli_r1": { "acc": 0.313, "acc_stderr": 0.014671272822977892 }, "anli_r2": { "acc": 0.341, "acc_stderr": 0.014998131348402707 }, "anli_r3": { "acc": 0.3283333333333333, "acc_stderr": 0.013562032919529019 }, "cb": { "acc": 0.4107142857142857, "acc_stderr": 0.0663363415035954, "f1": 0.3035294117647059 }, "copa": { "acc": 0.8, "acc_stderr": 0.04020151261036845 }, "hellaswag": { "acc": 0.4645488946425015, "acc_stderr": 0.0049772234853420255, "acc_norm": 0.6142202748456482, "acc_norm_stderr": 0.004857840934549179 }, "rte": { "acc": 0.51985559566787, "acc_stderr": 0.030072723167317184 }, "winogrande": { "acc": 0.6085240726124704, "acc_stderr": 0.013717487071290856 }, "storycloze_2016": { "acc": 0.7076429716729022, "acc_stderr": 0.010518239729787741 }, "boolq": { "acc": 0.5391437308868502, "acc_stderr": 0.008718214887614912 }, "arc_easy": { "acc": 0.6691919191919192, "acc_stderr": 0.009654540125986119, "acc_norm": 0.6637205387205387, "acc_norm_stderr": 0.009694178072725204 }, "arc_challenge": { "acc": 0.318259385665529, "acc_stderr": 0.013611993916971451, "acc_norm": 0.3378839590443686, "acc_norm_stderr": 0.013822047922283517 }, "sciq": { "acc": 0.92, "acc_stderr": 0.008583336977753655, "acc_norm": 0.918, "acc_norm_stderr": 0.008680515615523724 }, "piqa": { "acc": 0.7589771490750816, "acc_stderr": 0.009979042717267315, "acc_norm": 0.7704026115342764, "acc_norm_stderr": 0.009812682950815181 } }, "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 } }