|
{ |
|
"STSBenchmark": { |
|
"train": { |
|
"pearson": [ |
|
0.7450494648920531, |
|
0.0 |
|
], |
|
"spearman": [ |
|
0.718852932944271, |
|
0.0 |
|
], |
|
"nsamples": 5749 |
|
}, |
|
"dev": { |
|
"pearson": [ |
|
0.7506528902322174, |
|
6.334785308459189e-272 |
|
], |
|
"spearman": [ |
|
0.7572938795946844, |
|
1.7723543437102127e-279 |
|
], |
|
"nsamples": 1500 |
|
}, |
|
"test": { |
|
"pearson": [ |
|
0.7350173167948336, |
|
1.2934482649472062e-234 |
|
], |
|
"spearman": [ |
|
0.7263841319575137, |
|
1.6287041037900951e-226 |
|
], |
|
"nsamples": 1379 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7417281269891771, |
|
"mean": 0.7435732239730347, |
|
"wmean": 0.7444202119694965 |
|
}, |
|
"spearman": { |
|
"all": 0.731134165691079, |
|
"mean": 0.7341769814988229, |
|
"wmean": 0.7267396904100664 |
|
} |
|
} |
|
}, |
|
"SICKRelatedness": { |
|
"train": { |
|
"pearson": [ |
|
0.7406122998418166, |
|
0.0 |
|
], |
|
"spearman": [ |
|
0.6737860533258943, |
|
0.0 |
|
], |
|
"nsamples": 4500 |
|
}, |
|
"dev": { |
|
"pearson": [ |
|
0.7491355419681752, |
|
3.992619644206497e-91 |
|
], |
|
"spearman": [ |
|
0.6974671648657597, |
|
4.380991542566403e-74 |
|
], |
|
"nsamples": 500 |
|
}, |
|
"test": { |
|
"pearson": [ |
|
0.7341897490069431, |
|
0.0 |
|
], |
|
"spearman": [ |
|
0.6637347101284393, |
|
0.0 |
|
], |
|
"nsamples": 4927 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7377595629576476, |
|
"mean": 0.7413125302723117, |
|
"wmean": 0.7378539350890975 |
|
}, |
|
"spearman": { |
|
"all": 0.6699463146611633, |
|
"mean": 0.6783293094400311, |
|
"wmean": 0.6699901016623577 |
|
} |
|
} |
|
}, |
|
"eval_senteval-stsb_spearman": 0.7572938795946844, |
|
"eval_senteval-sickr_spearman": 0.6974671648657597, |
|
"eval_senteval-avg_sts": 0.7273805222302221 |
|
} |
|
|