Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Integrate BERT into Hedwig #11

Merged
merged 4 commits into from Apr 14, 2019

Conversation

Projects
None yet
2 participants
@achyudh
Copy link
Member

achyudh commented Apr 14, 2019

Changes:

  • Fix package imports

  • Update README.md

  • Fix bug due to TAR/AR attribute check

  • Add BERT models

  • Add BERT tokenizer

  • Return logits from the model.py

  • Remove unused classes in models/bert

  • Return logits from the model.py (#12)

  • Remove unused classes in models/bert (#13)

  • Add initial main file

  • Add args for BERT

  • Add partial support for BERT

  • Initialize training and optimization

  • Draft the structure of Trainers for BERT

  • Remove duplicate tokenizer

  • Add utils

  • Move optimization to utils

  • Add more structure for trainer

  • Refactor the trainer (#15)

  • Refactor the trainer

  • Add more edits

  • Add support for our datasets

  • Add evaluator

  • Split data4bert module into multiple processors

  • Refactor BERT tokenizer

  • Integrate BERT into Castor framework (#17)

  • Remove unused classes in models/bert

  • Split data4bert module into multiple processors

  • Refactor BERT tokenizer

  • Add multilabel support in BertTrainer

  • Add multilabel support in BertEvaluator

  • Add get_test_samples method in dataset processors

  • Fix args.py for BERT

  • Add support for Reuters, IMDB datasets for BERT

achyudh added some commits Apr 14, 2019

Integrate BERT into Hedwig (#29)
* Fix package imports

* Update README.md

* Fix bug due to TAR/AR attribute check

* Add BERT models

* Add BERT tokenizer

* Return logits from the model.py

* Remove unused classes in models/bert

* Return logits from the model.py (#12)

* Remove unused classes in models/bert (#13)

* Add initial main file

* Add args for BERT

* Add partial support for BERT

* Initialize training and optimization

* Draft the structure of Trainers for BERT

* Remove duplicate tokenizer

* Add utils

* Move optimization to utils

* Add more structure for trainer

* Refactor the trainer (#15)

* Refactor the trainer

* Add more edits

* Add support for our datasets

* Add evaluator

* Split data4bert module into multiple processors

* Refactor BERT tokenizer

* Integrate BERT into Castor framework (#17)

* Remove unused classes in models/bert

* Split data4bert module into multiple processors

* Refactor BERT tokenizer

* Add multilabel support in BertTrainer

* Add multilabel support in BertEvaluator

* Add get_test_samples method in dataset processors

* Fix args.py for BERT

* Add support for Reuters, IMDB datasets for BERT

* Revert "Integrate BERT into Castor framework (#17)"

This reverts commit e4244ec.

* Fix paths to datasets in dataset classes and args

* Add SST dataset

* Add hedwig-data instructions to README.md

* Fix KimCNN README

* Fix RegLSTM README

* Fix typos in README

* Remove trec_eval from README

* Add tensorboardX to requirements.txt

* Rename processors module to bert_processors

* Add method to print metrics after training

* Add model check-pointing and early stopping for BERT

* Add logos

* Update README.md

* Fix code comments in classification trainer

* Add support for AAPD, Sogou, AGNews and Yelp2014

* Fix bug that deleted saved models

* Update README for HAN

* Update README for XML-CNN

* Remove redundant TODOs from the READMEs

* Fix logo in README.md

* Update README for Char-CNN

* Fix all the READMEs

* Resolve conflict

* Fix Typos

* Re-Add SST2 Processor

* Add support for evaluating trained model

* Update args.py

* Resolve issues due to DataParallel wrapper on saved model

* Remove redundant Yelp processor

* Fix bug for safely creating the saving directory

* Change checkpoint paths to timestamps

* Remove unwanted string.strip() from tokenizer

* Create save path if it doesn't exist

* Decouple model checkpoints from code

* Remove model choice restrictions for BERT

* Remove model/distill driver

* Simplify checkpoint directory creation
@Ashutosh-Adhikari

This comment has been minimized.

Copy link
Member

Ashutosh-Adhikari commented Apr 14, 2019

Why would we create a duplicate PR? Or is there something that I am missing?

@achyudh

This comment has been minimized.

Copy link
Member Author

achyudh commented Apr 14, 2019

I cannot resolve conflicts and push directly to karkaroff. It has to be on a fork I have write access to.

@Ashutosh-Adhikari

This comment has been minimized.

Copy link
Member

Ashutosh-Adhikari commented Apr 14, 2019

Don't worry, I have resolved the conflicts. Please close this duplitcate PR. Thanks

@achyudh

This comment has been minimized.

Copy link
Member Author

achyudh commented Apr 14, 2019

Hmm, I don't see any changes in your original pull request yet

@achyudh achyudh force-pushed the achyudh:master branch from 6ff9a72 to fff8e0a Apr 14, 2019

@Ashutosh-Adhikari Ashutosh-Adhikari requested review from Ashutosh-Adhikari and removed request for daemon Apr 14, 2019

@Ashutosh-Adhikari
Copy link
Member

Ashutosh-Adhikari left a comment

LGTM.

@Ashutosh-Adhikari Ashutosh-Adhikari merged commit 7d24958 into castorini:master Apr 14, 2019

Ashutosh-Adhikari added a commit to Ashutosh-Adhikari/hedwig that referenced this pull request Apr 18, 2019

Sync castorini/hedwig Master (#9)
* Fix package imports

* Update README.md

* Remove extraneous package requirements

* Remove tqdm from requirements

* Fix bug due to TAR/AR attribute check

* Update README.md

*  Integrate BERT into Hedwig (#29) (castorini#11)

* Fix package imports

* Update README.md

* Fix bug due to TAR/AR attribute check

* Add BERT models

* Add BERT tokenizer

* Return logits from the model.py

* Remove unused classes in models/bert

* Return logits from the model.py (castorini#12)

* Remove unused classes in models/bert (castorini#13)

* Add initial main file

* Add args for BERT

* Add partial support for BERT

* Initialize training and optimization

* Draft the structure of Trainers for BERT

* Remove duplicate tokenizer

* Add utils

* Move optimization to utils

* Add more structure for trainer

* Refactor the trainer (#15)

* Refactor the trainer

* Add more edits

* Add support for our datasets

* Add evaluator

* Split data4bert module into multiple processors

* Refactor BERT tokenizer

* Integrate BERT into Castor framework (#17)

* Remove unused classes in models/bert

* Split data4bert module into multiple processors

* Refactor BERT tokenizer

* Add multilabel support in BertTrainer

* Add multilabel support in BertEvaluator

* Add get_test_samples method in dataset processors

* Fix args.py for BERT

* Add support for Reuters, IMDB datasets for BERT

* Revert "Integrate BERT into Castor framework (#17)"

This reverts commit e4244ec.

* Fix paths to datasets in dataset classes and args

* Add SST dataset

* Add hedwig-data instructions to README.md

* Fix KimCNN README

* Fix RegLSTM README

* Fix typos in README

* Remove trec_eval from README

* Add tensorboardX to requirements.txt

* Rename processors module to bert_processors

* Add method to print metrics after training

* Add model check-pointing and early stopping for BERT

* Add logos

* Update README.md

* Fix code comments in classification trainer

* Add support for AAPD, Sogou, AGNews and Yelp2014

* Fix bug that deleted saved models

* Update README for HAN

* Update README for XML-CNN

* Remove redundant TODOs from the READMEs

* Fix logo in README.md

* Update README for Char-CNN

* Fix all the READMEs

* Resolve conflict

* Fix Typos

* Re-Add SST2 Processor

* Add support for evaluating trained model

* Update args.py

* Resolve issues due to DataParallel wrapper on saved model

* Remove redundant Yelp processor

* Fix bug for safely creating the saving directory

* Change checkpoint paths to timestamps

* Remove unwanted string.strip() from tokenizer

* Create save path if it doesn't exist

* Decouple model checkpoints from code

* Remove model choice restrictions for BERT

* Remove model/distill driver

* Simplify checkpoint directory creation
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.