-
Notifications
You must be signed in to change notification settings - Fork 538
[Refactor] Refactor BERT with new data preprocessing #1124
Conversation
deleting trailing white space
merge from master
merge from master
Job PR-1124/7 is complete. |
@zburning please resolve the conflicts. As the Bert results match reported performance and some XLNet results still show a gap, how about removing the XLNet changes from this PR to unblock this PR? |
Job PR-1124/9 is complete. |
Job PR-1124/10 is complete. |
scripts/bert/finetune_classifier.py
Outdated
parser.add_argument('--bert_dataset', | ||
type=str, | ||
default='book_corpus_wiki_en_uncased', | ||
choices=[ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think we need to add an API nlp.data.list_datasets()
to list all available datasets in gluonnlp. Otherwise every time a new model is added, we need to revise the choice list in the script..
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Please delete scripts/bert/test-682b5d15.bpe
. I think it's included by mistake.
Job PR-1124/13 is complete. |
Job PR-1124/14 is complete. |
Job PR-1124/15 is complete. |
Job PR-1124/16 is complete. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thank you!
Description
New data preprocessing.
Refactor BERT squad script.
Add XLNet squad script.
Update & add corresponding results.
Checklist
Essentials
Changes
Comments