fix: fix BF16_Optimizer compatibility issue#2152
Merged
tjruwase merged 2 commits intodeepspeedai:masterfrom Jul 28, 2022
Merged
fix: fix BF16_Optimizer compatibility issue#2152tjruwase merged 2 commits intodeepspeedai:masterfrom
tjruwase merged 2 commits intodeepspeedai:masterfrom
Conversation
shjwudp
requested review from
RezaYazdaniAminabadi,
ShadenSmith,
arashb,
awan-10,
cli99,
conglongli,
duli2012,
eltonzheng,
jeffra,
minjiaz,
mrwyattii,
samadejacobs,
samyam,
tjruwase,
xiaoxiawu-microsoft and
yaozhewei
as code owners
Contributor
|
@shjwudp, thanks for this PR. Can you share a bit more context on when this fails? |
Contributor
Author
OK, this is really an edge case, in fairseq's Adafactor implementation, the RMS is calculated by the formula |
tjruwase
approved these changes
Jul 28, 2022
Contributor
|
Interesting, thanks for sharing. So, to clarify, are you applying bf16_optimizer to adafactor for large model training? If so, we would be very interested in your experience. I suspect there might be issues with checkpoint load/stores, perhaps :). |
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fix BF16_Optimizer compatibility issue with optimizer state 0-dim tensor,
tensor.narrowdoes not support 0-dim tensor.