{ "STSBenchmark": { "train": { "pearson": [ 0.7078537910606651, 0.0 ], "spearman": [ 0.7005999583866984, 0.0 ], "nsamples": 5749 }, "dev": { "pearson": [ 0.7192800747133679, 3.077700364928066e-239 ], "spearman": [ 0.7379237505860065, 4.277474410967731e-258 ], "nsamples": 1500 }, "test": { "pearson": [ 0.6983884458054606, 2.940291533445568e-202 ], "spearman": [ 0.7136101793848104, 4.3889157567246634e-215 ], "nsamples": 1379 }, "all": { "pearson": { "all": 0.7084868825859301, "mean": 0.7085074371931644, "wmean": 0.7083274482665213 }, "spearman": { "all": 0.7134156978222834, "mean": 0.7173779627858385, "wmean": 0.7091681993527809 } } }, "SICKRelatedness": { "train": { "pearson": [ 0.7474648285643389, 0.0 ], "spearman": [ 0.6940199688267912, 0.0 ], "nsamples": 4500 }, "dev": { "pearson": [ 0.7666627901165247, 6.873435561530908e-98 ], "spearman": [ 0.7253075282545358, 8.79855875263332e-83 ], "nsamples": 500 }, "test": { "pearson": [ 0.7471456909275643, 0.0 ], "spearman": [ 0.6877954280401497, 0.0 ], "nsamples": 4927 }, "all": { "pearson": { "all": 0.7481870904024901, "mean": 0.753757769869476, "wmean": 0.7482733900269867 }, "spearman": { "all": 0.6925290217821645, "mean": 0.7023743083738255, "wmean": 0.6925064669891857 } } }, "eval_senteval-stsb_spearman": 0.7379237505860065, "eval_senteval-sickr_spearman": 0.7253075282545358, "eval_senteval-avg_sts": 0.7316156394202711 }