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
[FLAVA] Make projections part of the core model #106
Conversation
[ghstack-poisoned]
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]
[ghstack-poisoned]
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]
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]
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]
ghstack-source-id: e6b230c54929fdf73321869b783a88bcf7fcaca4 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 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. |
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