Update language_model README.md (#941)

Summary:
Adding a backslash in the convolutional language model training usage.
Pull Request resolved: https://github.com/pytorch/fairseq/pull/941

Differential Revision: D16581388

Pulled By: myleott

fbshipit-source-id: 7e2e05ecf13e86cb844dc5200d49f560c63b12ff

examples/language_model/README.md

@@ -82,7 +82,7 @@ $ fairseq-train --task language_modeling data-bin/wikitext-103 \
   --max-epoch 35 --arch fconv_lm_dauphin_wikitext103 --optimizer nag \
   --lr 1.0 --lr-scheduler reduce_lr_on_plateau --lr-shrink 0.5 \
   --clip-norm 0.1 --dropout 0.2 --weight-decay 5e-06 --criterion adaptive_loss \
-  --adaptive-softmax-cutoff 10000,20000,200000 --max-tokens 1024 --tokens-per-sample 1024
+  --adaptive-softmax-cutoff 10000,20000,200000 --max-tokens 1024 --tokens-per-sample 1024 \
   --ddp-backend=no_c10d
 
 # Evaluate: