cdec cfg 'cdec.ini' Loading the LM will be faster if you build a binary file. Reading ../example/nc-wmt11.en.srilm.gz ----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100 **************************************************************************************************** Seeding random number sequence to 1771918374 dtrain Parameters: k 100 N 4 T 1 scorer 'stupid_bleu' sample from 'kbest' filter 'uniq' learning rate 0.0001 gamma 0 loss margin 1 pairs 'XYX' hi lo 0.1 pair threshold 0 select weights 'last' l1 reg 0 'none' max pairs 4294967295 cdec cfg 'cdec.ini' input 'work/shard.1.0.in' refs 'work/shard.1.0.refs' output 'work/weights.1.1' weights in 'work/weights.0' (a dot represents 10 inputs) Iteration #1 of 1. 5 WEIGHTS Glue = -0.3178 WordPenalty = +0.11092 LanguageModel = +0.17269 LanguageModel_OOV = -0.13485 PhraseModel_0 = -0.45371 PhraseModel_1 = +0.38789 PhraseModel_2 = +0.75311 PhraseModel_3 = -0.38163 PhraseModel_4 = -0.58817 PhraseModel_5 = -0.0269 PhraseModel_6 = -0.27315 PassThrough = -0.16745 --- 1best avg score: 0.13169 (+0.13169) 1best avg model score: 24.226 (+24.226) avg # pairs: 1951.2 avg # rank err: 985.4 avg # margin viol: 951 non0 feature count: 12 avg list sz: 100 avg f count: 11.224 (time 0.42 min, 5 s/S) Writing weights file to 'work/weights.1.1' ... done --- Best iteration: 1 [SCORE 'stupid_bleu'=0.13169]. This took 0.41667 min.