|
{ |
|
"results": { |
|
"anli_r1": { |
|
"acc": 0.317, |
|
"acc_stderr": 0.014721675438880241 |
|
}, |
|
"anli_r2": { |
|
"acc": 0.358, |
|
"acc_stderr": 0.015167928865407559 |
|
}, |
|
"anli_r3": { |
|
"acc": 0.32166666666666666, |
|
"acc_stderr": 0.013490095282989521 |
|
}, |
|
"cb": { |
|
"acc": 0.5178571428571429, |
|
"acc_stderr": 0.06737697508644647, |
|
"f1": 0.3558162267839687 |
|
}, |
|
"copa": { |
|
"acc": 0.77, |
|
"acc_stderr": 0.04229525846816506 |
|
}, |
|
"hellaswag": { |
|
"acc": 0.44911372236606256, |
|
"acc_stderr": 0.0049638729368579396, |
|
"acc_norm": 0.5975901214897431, |
|
"acc_norm_stderr": 0.004893814890208308 |
|
}, |
|
"rte": { |
|
"acc": 0.49458483754512633, |
|
"acc_stderr": 0.030094698123239966 |
|
}, |
|
"winogrande": { |
|
"acc": 0.5651144435674822, |
|
"acc_stderr": 0.013932814110418025 |
|
}, |
|
"storycloze_2016": { |
|
"acc": 0.6996258685195083, |
|
"acc_stderr": 0.010600915927985021 |
|
}, |
|
"boolq": { |
|
"acc": 0.6204892966360857, |
|
"acc_stderr": 0.008487341975756834 |
|
}, |
|
"arc_easy": { |
|
"acc": 0.6418350168350169, |
|
"acc_stderr": 0.009838331651451841, |
|
"acc_norm": 0.6296296296296297, |
|
"acc_norm_stderr": 0.009908978578665753 |
|
}, |
|
"arc_challenge": { |
|
"acc": 0.28498293515358364, |
|
"acc_stderr": 0.013191348179838793, |
|
"acc_norm": 0.3293515358361775, |
|
"acc_norm_stderr": 0.013734057652635474 |
|
}, |
|
"sciq": { |
|
"acc": 0.918, |
|
"acc_stderr": 0.008680515615523727, |
|
"acc_norm": 0.919, |
|
"acc_norm_stderr": 0.00863212103213998 |
|
}, |
|
"piqa": { |
|
"acc": 0.7475516866158868, |
|
"acc_stderr": 0.010135665547362362, |
|
"acc_norm": 0.7453754080522307, |
|
"acc_norm_stderr": 0.010164432237060494 |
|
} |
|
}, |
|
"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 |
|
} |
|
} |