[FLAVA]Change some initialization orders and corresponding tests #105
Conversation
This file contains hidden or 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
[ghstack-poisoned]
This was referenced Jun 21, 2022
facebook-github-bot
added
the
CLA Signed
Codecov Report
@@ Coverage Diff @@
## gh/ankitade/4/base #105 +/- ##
=====================================================
Coverage ? 93.00%
=====================================================
Files ? 47
Lines ? 2758
Branches ? 0
=====================================================
Hits ? 2565
Misses ? 193
Partials ? 0 Continue to review full report at Codecov.
|
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
[ghstack-poisoned]
ankitade
changed the title
|
@ankitade has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
… tests" - Currently the projections are part of contrastive loss which means we need to use "flava for pretraining" for zero shot. This is weird since zero shot should just involve core model (and not pretraining model) - The next PR in this stack tried to fix it but broke the tests because of changing initialization order of several components - So splitting that PR into 2 to make sure my logic changes are not actually breaking anything 1. This PR which simply changes the initialization order of codebook and contrastive loss and changes the test assert values 2. Next PR which makes projections part of flava model and doesn't touch the tests Test plan pytest Differential Revision: [D37466221](https://our.internmc.facebook.com/intern/diff/D37466221) [ghstack-poisoned]
… tests" - Currently the projections are part of contrastive loss which means we need to use "flava for pretraining" for zero shot. This is weird since zero shot should just involve core model (and not pretraining model) - The next PR in this stack tried to fix it but broke the tests because of changing initialization order of several components - So splitting that PR into 2 to make sure my logic changes are not actually breaking anything 1. This PR which simply changes the initialization order of codebook and contrastive loss and changes the test assert values 2. Next PR which makes projections part of flava model and doesn't touch the tests Test plan pytest Differential Revision: [D37466221](https://our.internmc.facebook.com/intern/diff/D37466221) [ghstack-poisoned]
… tests" - Currently the projections are part of contrastive loss which means we need to use "flava for pretraining" for zero shot. This is weird since zero shot should just involve core model (and not pretraining model) - The next PR in this stack tried to fix it but broke the tests because of changing initialization order of several components - So splitting that PR into 2 to make sure my logic changes are not actually breaking anything 1. This PR which simply changes the initialization order of codebook and contrastive loss and changes the test assert values 2. Next PR which makes projections part of flava model and doesn't touch the tests Test plan pytest Differential Revision: [D37466221](https://our.internmc.facebook.com/intern/diff/D37466221) [ghstack-poisoned]
|
@ankitade has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
… tests" - Currently the projections are part of contrastive loss which means we need to use "flava for pretraining" for zero shot. This is weird since zero shot should just involve core model (and not pretraining model) - The next PR in this stack tried to fix it but broke the tests because of changing initialization order of several components - So splitting that PR into 2 to make sure my logic changes are not actually breaking anything 1. This PR which simply changes the initialization order of codebook and contrastive loss and changes the test assert values 2. Next PR which makes projections part of flava model and doesn't touch the tests Test plan pytest Differential Revision: [D37466221](https://our.internmc.facebook.com/intern/diff/D37466221) [ghstack-poisoned]
ebsmothers
approved these changes
Jun 30, 2022
This was referenced Jul 4, 2022
… tests" - Currently the projections are part of contrastive loss which means we need to use "flava for pretraining" for zero shot. This is weird since zero shot should just involve core model (and not pretraining model) - The next PR in this stack tried to fix it but broke the tests because of changing initialization order of several components - So splitting that PR into 2 to make sure my logic changes are not actually breaking anything 1. This PR which simply changes the initialization order of codebook and contrastive loss and changes the test assert values 2. Next PR which makes projections part of flava model and doesn't touch the tests Test plan pytest Differential Revision: [D37466221](https://our.internmc.facebook.com/intern/diff/D37466221) [ghstack-poisoned]
|
@ankitade has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
5 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. |
|
@ankitade has imported this pull request. If you are a Facebook employee, you can view this diff on Phabricator. |
… tests" - Currently the projections are part of contrastive loss which means we need to use "flava for pretraining" for zero shot. This is weird since zero shot should just involve core model (and not pretraining model) - The next PR in this stack tried to fix it but broke the tests because of changing initialization order of several components - So splitting that PR into 2 to make sure my logic changes are not actually breaking anything 1. This PR which simply changes the initialization order of codebook and contrastive loss and changes the test assert values 2. Next PR which makes projections part of flava model and doesn't touch the tests Test plan pytest Differential Revision: [D37466221](https://our.internmc.facebook.com/intern/diff/D37466221) [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
4 participants
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.
Test plan
pytest
Stack from ghstack (oldest at bottom):
Differential Revision: D37466221