{ "STSBenchmark": { "train": { "pearson": [ 0.700217766857111, 0.0 ], "spearman": [ 0.694596243514894, 0.0 ], "nsamples": 5749 }, "dev": { "pearson": [ 0.7188725565702827, 7.642460243707613e-239 ], "spearman": [ 0.7430861317995934, 1.3229042265692801e-263 ], "nsamples": 1500 }, "test": { "pearson": [ 0.6697149917661123, 3.5510311886663796e-180 ], "spearman": [ 0.7028355722100523, 6.396511507534624e-206 ], "nsamples": 1379 }, "all": { "pearson": { "all": 0.7003515412165919, "mean": 0.6962684383978353, "wmean": 0.698585738312752 }, "spearman": { "all": 0.708944371429387, "mean": 0.7135059825081799, "wmean": 0.7043432146203266 } } }, "SICKRelatedness": { "train": { "pearson": [ 0.7900787687078513, 0.0 ], "spearman": [ 0.7162798220982042, 0.0 ], "nsamples": 4500 }, "dev": { "pearson": [ 0.7941456305052318, 8.704175570070149e-110 ], "spearman": [ 0.7323591663810709, 3.70700656086251e-85 ], "nsamples": 500 }, "test": { "pearson": [ 0.7827901659487767, 0.0 ], "spearman": [ 0.7066436772359563, 0.0 ], "nsamples": 4927 }, "all": { "pearson": { "all": 0.7866207722959027, "mean": 0.7890048550539532, "wmean": 0.7866661047715896 }, "spearman": { "all": 0.7122486034563766, "mean": 0.7184275552384105, "wmean": 0.7123070595722788 } } }, "eval_senteval-stsb_spearman": 0.7430861317995934, "eval_senteval-sickr_spearman": 0.7323591663810709, "eval_senteval-avg_sts": 0.7377226490903321 }