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.3.0.in'
                  output 'work/weights.3.0'
(a dot per input)
Iteration #1 of 1.
 .. 1
WEIGHTS
              Glue = -0.09
       WordPenalty = +0.32442
     LanguageModel = +2.5769
 LanguageModel_OOV = -0.009
     PhraseModel_0 = -0.58972
     PhraseModel_1 = +0.063691
     PhraseModel_2 = +0.5366
     PhraseModel_3 = +0.12867
     PhraseModel_4 = -1.9801
     PhraseModel_5 = +0.018
     PhraseModel_6 = -0.486
       PassThrough = -0.09
        ---
       1best avg score: 0.034204 (+0.034204)
 1best avg model score: 0
           avg # pairs: 1700
   non-0 feature count: 12
           avg list sz: 100
           avg f count: 10.8
(time 0.1 min, 6 s/S)

---
Best iteration: 1 [GOLD = 0.034204].
This took 0.1 min.