Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
chenpangpang
transformers
Commits
28d5700a
Unverified
Commit
28d5700a
authored
Sep 21, 2021
by
Lowin
Committed by
GitHub
Sep 20, 2021
Browse files
fix research_projects/mlm_wwm readme.md examples (#13646)
the variables of run example is not correct
parent
002a078a
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
17 additions
and
11 deletions
+17
-11
examples/research_projects/mlm_wwm/README.md
examples/research_projects/mlm_wwm/README.md
+17
-11
No files found.
examples/research_projects/mlm_wwm/README.md
View file @
28d5700a
...
@@ -60,33 +60,39 @@ You could run the following:
...
@@ -60,33 +60,39 @@ You could run the following:
```
bash
```
bash
export
TRAIN_FILE
=
/path/to/
dataset/wiki.train.raw
export
TRAIN_FILE
=
/path/to/
train/file
export
LTP_RESOURCE
=
/path/to/ltp/tokenizer
export
LTP_RESOURCE
=
/path/to/ltp/tokenizer
export
BERT_RESOURCE
=
/path/to/bert/tokenizer
export
BERT_RESOURCE
=
/path/to/bert/tokenizer
export
SAVE_PATH
=
/path/to/data/ref.txt
export
SAVE_PATH
=
/path/to/data/ref.txt
python run_chinese_ref.py
\
python run_chinese_ref.py
\
--file_name
=
path_to_train_or_eval_file
\
--file_name
=
$TRAIN_FILE
\
--ltp
=
path_to_ltp_tokenizer
\
--ltp
=
$LTP_RESOURCE
\
--bert
=
path_to_bert_tokenizer
\
--bert
=
$BERT_RESOURCE
\
--save_path
=
path_to_reference_file
--save_path
=
$SAVE_PATH
```
```
Then you can run the script like this:
Then you can run the script like this:
```
bash
```
bash
export
TRAIN_FILE
=
/path/to/train/file
export
VALIDATION_FILE
=
/path/to/validation/file
export
TRAIN_REF_FILE
=
/path/to/train/chinese_ref/file
export
VALIDATION_REF_FILE
=
/path/to/validation/chinese_ref/file
export
OUTPUT_DIR
=
/tmp/test-mlm-wwm
python run_mlm_wwm.py
\
python run_mlm_wwm.py
\
--model_name_or_path
roberta-base
\
--model_name_or_path
roberta-base
\
--train_file
path_to_train_file
\
--train_file
$TRAIN_FILE
\
--validation_file
path_to_validation_file
\
--validation_file
$VALIDATION_FILE
\
--train_ref_file
path_to_train_chinese_ref_file
\
--train_ref_file
$TRAIN_REF_FILE
\
--validation_ref_file
path_to_validation_chinese_ref_file
\
--validation_ref_file
$VALIDATION_REF_FILE
\
--do_train
\
--do_train
\
--do_eval
\
--do_eval
\
--output_dir
/tmp/test-mlm-wwm
--output_dir
$OUTPUT_DIR
```
```
**Note1:**
On TPU, you should the flag
`--pad_to_max_length`
to make sure all your batches have the same length.
**Note1:**
On TPU, you should the flag
`--pad_to_max_length`
to make sure all your batches have the same length.
**Note2:**
And if you have any questions or something goes wrong when runing this code, don't hesitate to pin @wlhgtc.
**Note2:**
And if you have any questions or something goes wrong when runing this code, don't hesitate to pin @wlhgtc.
\ No newline at end of file
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment