{ "STSBenchmark": { "train": { "pearson": [ 0.73125161607048, 0.0 ], "spearman": [ 0.7150765613453124, 0.0 ], "nsamples": 5749 }, "dev": { "pearson": [ 0.7443000568532008, 6.40691279840157e-265 ], "spearman": [ 0.759890982808152, 1.6901750172343795e-282 ], "nsamples": 1500 }, "test": { "pearson": [ 0.7216210553290073, 3.539646733532031e-222 ], "spearman": [ 0.7304939228930519, 2.4834600870262812e-230 ], "nsamples": 1379 }, "all": { "pearson": { "all": 0.7322719424112719, "mean": 0.7323909094175627, "wmean": 0.7319808833295888 }, "spearman": { "all": 0.7295849518142924, "mean": 0.7351538223488387, "wmean": 0.7253317970625808 } } }, "SICKRelatedness": { "train": { "pearson": [ 0.7596859741218331, 0.0 ], "spearman": [ 0.7018231072465838, 0.0 ], "nsamples": 4500 }, "dev": { "pearson": [ 0.777647576791967, 1.9353259230163057e-102 ], "spearman": [ 0.7337127308506983, 1.2717377929862408e-85 ], "nsamples": 500 }, "test": { "pearson": [ 0.7566490759566877, 0.0 ], "spearman": [ 0.6936198984184592, 0.0 ], "nsamples": 4927 }, "all": { "pearson": { "all": 0.7589921709943909, "mean": 0.7646608756234959, "wmean": 0.7590833755598704 }, "spearman": { "all": 0.6992260214830822, "mean": 0.7097185788385804, "wmean": 0.6993578712141356 } } }, "eval_senteval-stsb_spearman": 0.759890982808152, "eval_senteval-sickr_spearman": 0.7337127308506983, "eval_senteval-avg_sts": 0.7468018568294252 }