[FLAVA] Make projections part of the core model #106
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This was referenced Jun 21, 2022
facebook-github-bot
added
the
CLA Signed
ankitade
added a commit
that referenced
this pull request
Jun 21, 2022
[ghstack-poisoned]
ankitade
added a commit
that referenced
this pull request
Jun 23, 2022
Codecov Report
@@ Coverage Diff @@
## gh/ankitade/5/base #106 +/- ##
=====================================================
Coverage ? 93.04%
=====================================================
Files ? 47
Lines ? 2776
Branches ? 0
=====================================================
Hits ? 2583
Misses ? 193
Partials ? 0 Continue to review full report at Codecov.
|
[ghstack-poisoned]
ankitade
added a commit
that referenced
this pull request
Jun 26, 2022
[ghstack-poisoned]
ankitade
added a commit
that referenced
this pull request
Jun 26, 2022
ghstack-source-id: a97330da33e2f83ddd0070427d01647d4948f64c Pull Request resolved: #106
Move projections from the contrastive loss to the core model This will allow users to use the model (instead of the pretraining model) for doing zero shot Also moved to using the translated the checkpoint. Test plan 1. pytest 2. python -m flava.train config=flava/configs/pretraining/debug.yaml 3. python -m flava.finetune config=flava/configs/finetuning/qnli.yaml [ghstack-poisoned]
ankitade
added a commit
that referenced
this pull request
Jun 28, 2022
ghstack-source-id: f8b9173211262db95c897ab5827b862e595cdd7e Pull Request resolved: #106
Move projections from the contrastive loss to the core model This will allow users to use the model (instead of the pretraining model) for doing zero shot Also moved to using the translated the checkpoint. Test plan 1. pytest 2. python -m flava.train config=flava/configs/pretraining/debug.yaml 3. python -m flava.finetune config=flava/configs/finetuning/qnli.yaml [ghstack-poisoned]
ankitade
added a commit
that referenced
this pull request
Jun 28, 2022
ghstack-source-id: 4844b172f52d41979f5dcd74323105152d90df69 Pull Request resolved: #106
|
@ankitade has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
Move projections from the contrastive loss to the core model This will allow users to use the model (instead of the pretraining model) for doing zero shot Also moved to using the translated the checkpoint. Test plan 1. pytest 2. python -m flava.train config=flava/configs/pretraining/debug.yaml 3. python -m flava.finetune config=flava/configs/finetuning/qnli.yaml Differential Revision: [D37481127](https://our.internmc.facebook.com/intern/diff/D37481127) [ghstack-poisoned]
ankitade
added a commit
that referenced
this pull request
Jun 30, 2022
ghstack-source-id: e6b230c54929fdf73321869b783a88bcf7fcaca4 Pull Request resolved: #106
This was referenced Jul 4, 2022
ebsmothers
approved these changes
Jul 15, 2022
Move projections from the contrastive loss to the core model This will allow users to use the model (instead of the pretraining model) for doing zero shot Also moved to using the translated the checkpoint. Test plan 1. pytest 2. python -m flava.train config=flava/configs/pretraining/debug.yaml 3. python -m flava.finetune config=flava/configs/finetuning/qnli.yaml Differential Revision: [D37481127](https://our.internmc.facebook.com/intern/diff/D37481127) [ghstack-poisoned]
|
@ankitade has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
Move projections from the contrastive loss to the core model This will allow users to use the model (instead of the pretraining model) for doing zero shot Also moved to using the translated the checkpoint. Test plan 1. pytest 2. python -m flava.train config=flava/configs/pretraining/debug.yaml 3. python -m flava.finetune config=flava/configs/finetuning/qnli.yaml Differential Revision: [D37481127](https://our.internmc.facebook.com/intern/diff/D37481127) [ghstack-poisoned]
|
@ankitade has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
4 similar comments
|
@ankitade has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
|
@ankitade has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
|
@ankitade has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
|
@ankitade has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
Move projections from the contrastive loss to the core model This will allow users to use the model (instead of the pretraining model) for doing zero shot Also moved to using the translated the checkpoint. Test plan 1. pytest 2. python -m flava.train config=flava/configs/pretraining/debug.yaml 3. python -m flava.finetune config=flava/configs/finetuning/qnli.yaml Differential Revision: [D37481127](https://our.internmc.facebook.com/intern/diff/D37481127) [ghstack-poisoned]
|
@ankitade has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Move projections from the contrastive loss to the core model
This will allow users to use the model (instead of the pretraining model) for doing zero shot
Also moved to using the translated the checkpoint.
Test plan
Stack from ghstack (oldest at bottom):
Differential Revision: D37481127