Loading the LM will be faster if you build a binary file.
Reading ../standard/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
****************************************************************************************************
dtrain
Parameters:
                       k 100
                       N 4
                       T 1
           learning rate 0.0001
            error margin 1
                  l1 reg 0
            decoder conf 'cdec.ini'
                   input 'work/shard.2.0.in'
                  output 'work/weights.2.1'
              weights in 'work/weights.0'
(a dot per input)
Iteration #1 of 1.
 .... 3
WEIGHTS
              Glue = -0.76608
       WordPenalty = +0.15938
     LanguageModel = +1.5897
 LanguageModel_OOV = -0.521
     PhraseModel_0 = -0.58348
     PhraseModel_1 = +0.29828
     PhraseModel_2 = +0.78493
     PhraseModel_3 = +0.083222
     PhraseModel_4 = -0.93843
     PhraseModel_5 = +0.02435
     PhraseModel_6 = -0.27382
       PassThrough = -0.55115
        ---
       1best avg score: 0.12881 (+0.12881)
 1best avg model score: -9.6731
           avg # pairs: 2020.3
   non-0 feature count: 12
           avg list sz: 100
           avg f count: 12
(time 0.32 min, 6 s/S)

---
Best iteration: 1 [GOLD = 0.12881].
This took 0.31667 min.