{ "STSBenchmark": { "train": { "pearson": [ 0.7675016313639117, 0.0 ], "spearman": [ 0.7404488937353225, 0.0 ], "nsamples": 5749 }, "dev": { "pearson": [ 0.7658521041744508, 1.4020329449305176e-289 ], "spearman": [ 0.7730453513050343, 2.066561283121993e-298 ], "nsamples": 1500 }, "test": { "pearson": [ 0.7623056519318484, 1.8448021245198884e-262 ], "spearman": [ 0.7572290027800557, 5.3120116722114526e-257 ], "nsamples": 1379 }, "all": { "pearson": { "all": 0.7647570029076096, "mean": 0.7652197958234037, "wmean": 0.7663843913985655 }, "spearman": { "all": 0.7534738635333297, "mean": 0.7569077492734708, "wmean": 0.7487978108339844 } } }, "SICKRelatedness": { "train": { "pearson": [ 0.7707517065205873, 0.0 ], "spearman": [ 0.6949522587450165, 0.0 ], "nsamples": 4500 }, "dev": { "pearson": [ 0.778349180191507, 9.711324138536703e-103 ], "spearman": [ 0.7176593438481393, 2.743332620783351e-80 ], "nsamples": 500 }, "test": { "pearson": [ 0.7642987657770804, 0.0 ], "spearman": [ 0.6847455515560564, 0.0 ], "nsamples": 4927 }, "all": { "pearson": { "all": 0.7678373187987577, "mean": 0.7711332174963915, "wmean": 0.7679316297393041 }, "spearman": { "all": 0.6909477744903625, "mean": 0.6991190513830707, "wmean": 0.6910301368785469 } } }, "eval_senteval-stsb_spearman": 0.7730453513050343, "eval_senteval-sickr_spearman": 0.7176593438481393, "eval_senteval-avg_sts": 0.7453523475765869 }