|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.34, |
|
"acc_stderr": 0.014987482264363937 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.34, |
|
"acc_stderr": 0.014987482264363937 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.3408333333333333, |
|
"acc_stderr": 0.013688600793296939 |
|
}, |
|
"cb": { |
|
"acc": 0.375, |
|
"acc_stderr": 0.06527912098338669, |
|
"f1": 0.1818181818181818 |
|
}, |
|
"copa": { |
|
"acc": 0.77, |
|
"acc_stderr": 0.04229525846816506 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.4060944035052778, |
|
"acc_stderr": 0.004900988997414227, |
|
"acc_norm": 0.5160326628161721, |
|
"acc_norm_stderr": 0.004987215542259667 |
|
}, |
|
"rte": { |
|
"acc": 0.5487364620938628, |
|
"acc_stderr": 0.029953149241808946 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5430149960536701, |
|
"acc_stderr": 0.01400038676159829 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6739711384286478, |
|
"acc_stderr": 0.010839964752045184 |
|
}, |
|
"boolq": { |
|
"acc": 0.5318042813455658, |
|
"acc_stderr": 0.008727345583419184 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.5694444444444444, |
|
"acc_stderr": 0.010160345396860075, |
|
"acc_norm": 0.5151515151515151, |
|
"acc_norm_stderr": 0.010255071794531504 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.24744027303754265, |
|
"acc_stderr": 0.01261035266329267, |
|
"acc_norm": 0.2858361774744027, |
|
"acc_norm_stderr": 0.013203196088537369 |
|
}, |
|
"sciq": { |
|
"acc": 0.833, |
|
"acc_stderr": 0.011800434324644594, |
|
"acc_norm": 0.754, |
|
"acc_norm_stderr": 0.013626065817750636 |
|
}, |
|
"piqa": { |
|
"acc": 0.7219804134929271, |
|
"acc_stderr": 0.010453117358332802, |
|
"acc_norm": 0.7247007616974973, |
|
"acc_norm_stderr": 0.01042142927736953 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |