facebookresearch/fairseq
1
1
Fork 0
mirror of https://github.com/facebookresearch/fairseq.git synced 2024-09-19 21:30:55 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md (#679)

Browse Source 
Summary:
Add missing backslash.
Pull Request resolved: https://github.com/pytorch/fairseq/pull/679

Differential Revision: D15122270

Pulled By: myleott

fbshipit-source-id: fbdfde648051294eaa9f7a4e0c4cfbc57491a718
This commit is contained in:
Myle Ott 2019-04-29 09:09:56 -07:00 committed by Facebook Github Bot
parent 849605a0fd
commit ace8f72418
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
examples/cross_lingual_language_model/README.md
View File

@ -25,7 +25,7 @@ mkdir -p monolingual_data/fairseq_processed
for lg in ar de en hi fr for lg in ar de en hi fr
do do
fairseq-preprocess -- \ fairseq-preprocess \
--task cross_lingual_lm \ --task cross_lingual_lm \
--srcdict monolingual_data/processed/vocab_mlm \ --srcdict monolingual_data/processed/vocab_mlm \
--only-source \ --only-source \
@ -54,9 +54,9 @@ done
Use the following command to train the model on 5 languages. Use the following command to train the model on 5 languages.
``` ```
fairseq-train -- \ fairseq-train \
--task cross_lingual_lm monolingual_data/processed \ --task cross_lingual_lm monolingual_data/processed \
--save-dir checkpoints/mlm --save-dir checkpoints/mlm \
--max-update 2400000 --save-interval 1 --no-epoch-checkpoints \ --max-update 2400000 --save-interval 1 --no-epoch-checkpoints \
--arch xlm_base \ --arch xlm_base \
--optimizer adam --lr-scheduler reduce_lr_on_plateau \ --optimizer adam --lr-scheduler reduce_lr_on_plateau \