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
****************************************************************************************************
  Example feature: Shape_S00000_T00000
dtrain
Parameters:
                       k 100
                       N 4
                       T 1
           learning rate 0.0001
                  margin 1
                  l1 reg 0
            decoder conf 'cdec.ini'
                   input 'work/shard.1.0'
                  output 'work/weights.1.1'
              weights in 'work/weights.0'
(1 dot per processed input)
Iteration #1 of 1.
 ... 3
WEIGHTS
              Glue = +0.4661
       WordPenalty = +0.07374
     LanguageModel = +0.3354
 LanguageModel_OOV = -0.6514
     PhraseModel_0 = -0.4878
     PhraseModel_1 = +1.085
     PhraseModel_2 = +1.48
     PhraseModel_3 = -0.03441
     PhraseModel_4 = -0.5739
     PhraseModel_5 = +0.1023
     PhraseModel_6 = -0.3455
       PassThrough = -0.3826
        ---
       1best avg score: 10.18 (+10.18)
 1best avg model score: +71.15
         avg # updates: 2121
   non-0 feature count: 2275
           avg f count: 150.8
           avg list sz: 100
(time 0.15 min, 3 s/S)

---
Best iteration: 1 [GOLD = 10.18].
This took 0.15 min.