missing MLM traning files for replication?

mawentao277 / CharBERT

CharBERT: Character-aware Pre-trained Language Model (COLING2020)

Apache License 2.0

117 stars 28 forks source link

Open free-variation opened 3 years ago

free-variation commented 3 years ago

Hello,

I am trying to reproduce your results. The mlm.sh file references training and test data files that I do not see in your repo:

--train_data_file $DATA_DIR/testdata/mlm_pretrain_enwiki.train.t \
--eval_data_file $DATA_DIR/testdata/mlm_pretrain_enwiki.test.t \

Any help appreciated.

CsAbdulelah commented 2 years ago

Hi, I have the same problem could you find any solution?