|
{ |
|
"STSBenchmark": { |
|
"train": { |
|
"pearson": [ |
|
0.759143306453737, |
|
0.0 |
|
], |
|
"spearman": [ |
|
0.732317209733238, |
|
0.0 |
|
], |
|
"nsamples": 5749 |
|
}, |
|
"dev": { |
|
"pearson": [ |
|
0.7746081783379711, |
|
2.2556430824992415e-300 |
|
], |
|
"spearman": [ |
|
0.7800424504336374, |
|
2.5466091811087085e-307 |
|
], |
|
"nsamples": 1500 |
|
}, |
|
"test": { |
|
"pearson": [ |
|
0.7580850707783013, |
|
6.51859239939566e-258 |
|
], |
|
"spearman": [ |
|
0.7560754511600052, |
|
8.850873074119353e-256 |
|
], |
|
"nsamples": 1379 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7620304519086235, |
|
"mean": 0.7639455185233365, |
|
"wmean": 0.7616627780381048 |
|
}, |
|
"spearman": { |
|
"all": 0.7488342650348635, |
|
"mean": 0.7561450371089601, |
|
"wmean": 0.7444116088962087 |
|
} |
|
} |
|
}, |
|
"SICKRelatedness": { |
|
"train": { |
|
"pearson": [ |
|
0.7660762263543586, |
|
0.0 |
|
], |
|
"spearman": [ |
|
0.6943387839868075, |
|
0.0 |
|
], |
|
"nsamples": 4500 |
|
}, |
|
"dev": { |
|
"pearson": [ |
|
0.7787463535407387, |
|
6.565381473913046e-103 |
|
], |
|
"spearman": [ |
|
0.724076491124677, |
|
2.2464753888818782e-82 |
|
], |
|
"nsamples": 500 |
|
}, |
|
"test": { |
|
"pearson": [ |
|
0.7585953923013815, |
|
0.0 |
|
], |
|
"spearman": [ |
|
0.6847050750070173, |
|
0.0 |
|
], |
|
"nsamples": 4927 |
|
}, |
|
"all": { |
|
"pearson": { |
|
"all": 0.7629449380408607, |
|
"mean": 0.7678059907321595, |
|
"wmean": 0.7630014801283258 |
|
}, |
|
"spearman": { |
|
"all": 0.6909722716792152, |
|
"mean": 0.7010401167061673, |
|
"wmean": 0.6910551705512789 |
|
} |
|
} |
|
}, |
|
"eval_senteval-stsb_spearman": 0.7800424504336374, |
|
"eval_senteval-sickr_spearman": 0.724076491124677, |
|
"eval_senteval-avg_sts": 0.7520594707791572 |
|
} |
|
|