Skip to content

Add a loss comparison script #2029

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.

Sign up for GitHub

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

Merged
fegin merged 15 commits into from
Nov 19, 2025
Merged

Add a loss comparison script #2029

Show file tree
Hide file tree
Changes from 13 commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
546847a
Update (base update)
fegin Nov 12, 2025
dd979ef
Update
fegin Nov 12, 2025
0e78d18
Update (base update)
fegin Nov 12, 2025
4b4e547
Update
fegin Nov 12, 2025
fa43b28
Update (base update)
fegin Nov 12, 2025
4f2b8bd
Update
fegin Nov 12, 2025
cbec465
Update (base update)
fegin Nov 13, 2025
74f9fb7
Update
fegin Nov 13, 2025
0cfde37
Update (base update)
fegin Nov 17, 2025
9bb1b33
Update
fegin Nov 17, 2025
e393a13
Update
fegin Nov 17, 2025
a53269f
Update
fegin Nov 17, 2025
88f37f6
Update
fegin Nov 19, 2025
67708b9
Update
fegin Nov 19, 2025
1425d8a
Update
fegin Nov 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions .github/workflows/integration_test_8gpu_features.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,5 +76,12 @@ jobs:
export TEST_WITH_ROCM=$([[ "${{ matrix.gpu-arch-type }}" == "rocm" ]] && echo 1 || echo 0)
python -m tests.integration_tests.run_tests --test_suite features $RUNNER_TEMP/artifacts-to-be-uploaded --ngpu 8

# Verify the accuracy.
echo "Checking FSDP4 v.s. HSDP2FSDP2TP2 accuracy parity"
export baseline_options="--parallelism.data_parallel_replicate_degree=1"
export test_options="--parallelism.data_parallel_replicate_degree=2 --parallelism.tensor_parallel_degree=2"
python3 scripts/loss_compare.py . . --baseline-options="${baseline_options}" --test-options="${test_options}" --steps=10 --job-dump-folder="${RUNNER_TEMP}/artifacts-to-be-uploaded/accuracy_comparison_outputs" --assert-equal --baseline-ngpus=4 --test-ngpus=8 --steps=1
Copy link
Contributor

@tianyu-l tianyu-l Nov 19, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Would this be able to pass the failure to CI? In the past we've seen errors not propagated to CI, so we weren't be able to detect failures.

Copy link
Contributor Author

@fegin fegin Nov 19, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Didn't that happened before. My guess is yes as I saw the error earlier. But let's test it out.

Copy link
Contributor Author

@fegin fegin Nov 19, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, the error propagates correctly. https://github.com/pytorch/torchtitan/actions/runs/19486677666/job/55770375464?pr=2029


# Cleanup the checkpoints so that we don't waste network bandwidth and time.
rm -rf $RUNNER_TEMP/artifacts-to-be-uploaded/*/checkpoint
rm -rf artifacts-to-be-uploaded/*/checkpoint
Loading
Loading