{ "STSBenchmark": { "train": { "pearson": [ 0.7868313677903059, 0.0 ], "spearman": [ 0.7533061602723176, 0.0 ], "nsamples": 5749 }, "dev": { "pearson": [ 0.8010234738701788, 0.0 ], "spearman": [ 0.8010173901569266, 0.0 ], "nsamples": 1500 }, "test": { "pearson": [ 0.7766524771374954, 1.1662374252806932e-278 ], "spearman": [ 0.7638460069862814, 3.8220116833205965e-264 ], "nsamples": 1379 }, "all": { "pearson": { "all": 0.7882517084559206, "mean": 0.7881691062659933, "wmean": 0.7876718254757005 }, "spearman": { "all": 0.7668425138024548, "mean": 0.7727231858051752, "wmean": 0.7632854478761041 } } }, "SICKRelatedness": { "train": { "pearson": [ 0.7853064744370001, 0.0 ], "spearman": [ 0.7045889188784015, 0.0 ], "nsamples": 4500 }, "dev": { "pearson": [ 0.7952406911697713, 2.6811654216760936e-110 ], "spearman": [ 0.7309801454276812, 1.0951577254305346e-84 ], "nsamples": 500 }, "test": { "pearson": [ 0.7794843403240526, 0.0 ], "spearman": [ 0.6977349592492605, 0.0 ], "nsamples": 4927 }, "all": { "pearson": { "all": 0.7828650051750712, "mean": 0.7866771686436079, "wmean": 0.7829171779317007 }, "spearman": { "all": 0.7025121676824595, "mean": 0.7111013411851145, "wmean": 0.702516404944873 } } }, "eval_senteval-stsb_spearman": 0.8010173901569266, "eval_senteval-sickr_spearman": 0.7309801454276812, "eval_senteval-avg_sts": 0.7659987677923039 }