{ "results": { "anli_r1": { "acc": 0.328, "acc_stderr": 0.014853842487270336 }, "anli_r2": { "acc": 0.33, "acc_stderr": 0.014876872027456738 }, "anli_r3": { "acc": 0.35083333333333333, "acc_stderr": 0.013782212417178204 }, "cb": { "acc": 0.5, "acc_stderr": 0.06741998624632421, "f1": 0.34491725768321513 }, "copa": { "acc": 0.73, "acc_stderr": 0.04461960433384741 }, "hellaswag": { "acc": 0.4425413264289982, "acc_stderr": 0.004956724392646535, "acc_norm": 0.5784704242182832, "acc_norm_stderr": 0.00492794806148606 }, "rte": { "acc": 0.5018050541516246, "acc_stderr": 0.030096267148976626 }, "winogrande": { "acc": 0.5493291239147593, "acc_stderr": 0.01398392886904024 }, "storycloze_2016": { "acc": 0.6937466595403528, "acc_stderr": 0.010659088460112754 }, "boolq": { "acc": 0.5737003058103975, "acc_stderr": 0.008649531625805671 }, "arc_easy": { "acc": 0.5761784511784511, "acc_stderr": 0.010140006095213603, "acc_norm": 0.5374579124579124, "acc_norm_stderr": 0.010230952104570798 }, "arc_challenge": { "acc": 0.26791808873720135, "acc_stderr": 0.012942030195136426, "acc_norm": 0.2858361774744027, "acc_norm_stderr": 0.013203196088537369 }, "sciq": { "acc": 0.836, "acc_stderr": 0.011715000693181316, "acc_norm": 0.788, "acc_norm_stderr": 0.01293148186493804 }, "piqa": { "acc": 0.7437431991294886, "acc_stderr": 0.010185787831565056, "acc_norm": 0.7383025027203483, "acc_norm_stderr": 0.010255630772708229 } }, "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 } }