Add ComputeLobprob Tests #244
Merged
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
Jack-Khuu
requested review from
JenniferWang,
Ritesh1905,
allenwang28,
casteryh and
joecummings
meta-cla
bot
added
the
CLA Signed
joecummings
reviewed
Sep 26, 2025
joecummings
reviewed
Sep 26, 2025
|
Can you revive some of these tests? https://github.com/meta-pytorch/forge/blob/0e1984195c39816082c8d770f8186dfb6f4be764/tests/unit_tests/actors/test_reference_actor.py#L17-L98 |
casteryh
reviewed
Sep 27, 2025
Did not realize these tests still existed. yup will revive |
photomz
pushed a commit
to photomz/forge
that referenced
this pull request
Oct 25, 2025
* Basic test + Move compute_logprobs to util ops * docstring * Rebase + add empty response test * Update math
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Outdated suggestions cannot be applied.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.
Moves
compute_logprobsfrom GRPO app toutils/ops.pyand adds basic tests for itAlso updated the logit slicing math, to an equivalent version based on TRL
Old
New
python -m apps.grpo.main --config apps/grpo/qwen3_1_7b.yamlwandb (main): torchforge/grpo-training/runs/gq9wjime
wandb (PR): torchforge/grpo-training/runs/ctirsyoa
pytest tests/unit_tests/util/test_compute_logprobs.py