dnrops
/
transformers
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Adding --do_lower_case for all uncased BERTs 

I had missed those, it should make sense to use them
This commit is contained in:
Davide Fiocco 2018-12-07 20:40:56 +01:00 committed by GitHub
parent 3ba5470eb8
commit c9f67e037c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -404,6 +404,7 @@ python run_squad.py \
--bert_model bert-base-uncased \
--do_train \
--do_predict \
--do_lower_case \
--train_file $SQUAD_DIR/train-v1.1.json \
--predict_file $SQUAD_DIR/dev-v1.1.json \
--train_batch_size 12 \
@ -438,6 +439,7 @@ python ./run_squad.py \
--bert_model bert-large-uncased \
--do_train \
--do_predict \
--do_lower_case \
--train_file $SQUAD_TRAIN \
--predict_file $SQUAD_EVAL \
--learning_rate 3e-5 \
@ -458,6 +460,7 @@ python ./run_squad.py \
--bert_model bert-large-uncased \
--do_train \
--do_predict \
--do_lower_case \
--train_file $SQUAD_TRAIN \
--predict_file $SQUAD_EVAL \
--learning_rate 3e-5 \