Skip to content

Add weight_decay in OptimizerConfig #364

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

Jump to bottom
Merged
pan-x-c merged 2 commits into from
Nov 4, 2025
Merged

Add weight_decay in OptimizerConfig #364

pan-x-c merged 2 commits into from
Nov 4, 2025

Conversation

@hiyuchang
Copy link
Collaborator

@hiyuchang hiyuchang commented Nov 4, 2025

Description

As the title says.

Checklist

Please check the following items before code is ready to be reviewed.

  • Code has passed all tests
  • Docstrings have been added/updated in Google Style
  • Documentation has been updated
  • Code is ready for review

@gemini-code-assist
Copy link
Contributor

gemini-code-assist bot commented Nov 4, 2025

Summary of Changes

Hello @hiyuchang, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces a new configuration option for optimizers, specifically weight_decay, into the OptimizerConfig class. This enhancement provides a standardized way to specify the weight decay parameter for optimization algorithms, allowing for more flexible and configurable regularization during model training.

Highlights

  • Configuration Update: A new field, weight_decay, has been added to the OptimizerConfig class within trinity/common/config.py.
  • Default Value: The weight_decay parameter is initialized with a default value of 0.01.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

gemini-code-assist[bot]
gemini-code-assist bot reviewed Nov 4, 2025
View reviewed changes
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request adds a weight_decay parameter to the OptimizerConfig. The change is straightforward and correctly integrated for the actor's optimizer configuration. However, I've pointed out a potential point of confusion regarding the critic's optimizer configuration, which is not synchronized from the same top-level config. This can lead to inconsistent settings between the actor and critic. I've also suggested adding a unit test to ensure the new parameter is correctly propagated to the actor's configuration.

@hiyuchang
Copy link
Collaborator Author

hiyuchang commented Nov 4, 2025

/unittest-module-common

@github-actions
Copy link

github-actions bot commented Nov 4, 2025

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
33 33 0 0 0 0 4m 55s

Tests

Test Name Status Flaky Duration
tests/common/config_test.py::TestConfig::test_all_examples_are_valid ✅ 40.4s
tests/common/config_test.py::TestConfig::test_config_flatten ✅ 39ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid ✅ 426ms
tests/common/config_test.py::TestConfig::test_default_workflow ✅ 90ms
tests/common/config_test.py::TestConfig::test_load_default_config ✅ 3.3s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly ✅ 91ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster ✅ 1.6s
tests/common/experience_test.py::TestEID::test_eid_properties ✅ 1ms
tests/common/experience_test.py::TestExperience::test_action_mask_and_logprobs_type ✅ 1ms
tests/common/experience_test.py::TestExperience::test_assertions ✅ 1ms
tests/common/experience_test.py::TestExperience::test_dpo_experience ✅ 1ms
tests/common/experience_test.py::TestExperience::test_gather ✅ 1ms
tests/common/experience_test.py::TestExperience::test_hf_datasets_conversion ✅ 14ms
tests/common/experience_test.py::TestExperience::test_multi_turn_experience ✅ 1ms
tests/common/experience_test.py::TestExperience::test_serialize_deserialize ✅ 1ms
tests/common/experience_test.py::TestExperience::test_single_turn_experience ✅ 1ms
tests/common/experience_test.py::TestExperience::test_to_dict ✅ 1ms
tests/common/experience_test.py::TestExperienceConversion::test_batch_conversion ✅ 1ms
tests/common/experience_test.py::TestExperienceConversion::test_dpo_experience_batch_conversion ✅ 1ms
tests/common/experience_test.py::TestExperienceConversion::test_experience_model_experience_conversion ✅ 1ms
tests/common/experience_test.py::TestExperienceConversion::test_gather_experiences_with_custom_fields ✅ 1ms
tests/common/experience_test.py::TestExperienceConversion::test_multiturn_experience_batch_converstion ✅ 1ms
tests/common/vllm_test.py::ModelWrapperTest_0::test_generate ✅ 52.4s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate ✅ 32.0s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate ✅ 43.6s
tests/common/vllm_test.py::TestModelLen_0::test_model_len ✅ 17.0s
tests/common/vllm_test.py::TestModelLen_1::test_model_len ✅ 16.8s
tests/common/vllm_test.py::TestAPIServer::test_api ✅ 22.7s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async ✅ 22.6s
tests/common/vllm_test.py::TestTokenizer::test_action_mask ✅ 243ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools ✅ 232ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls ✅ 19.7s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls ✅ 17.5s

Github Test Reporter by CTRF 💚

@hiyuchang
Copy link
Collaborator Author

hiyuchang commented Nov 4, 2025

/unittest-module-common

@github-actions
Copy link

github-actions bot commented Nov 4, 2025

Summary

Tests 📝 Passed ✅ Failed ❌ Skipped ⏭️ Other ❓ Flaky 🍂 Duration ⏱️
34 34 0 0 0 0 4m 56s

Tests

Test Name Status Flaky Duration
tests/common/config_test.py::TestConfig::test_all_examples_are_valid ✅ 40.6s
tests/common/config_test.py::TestConfig::test_config_flatten ✅ 38ms
tests/common/config_test.py::TestConfig::test_continue_from_checkpoint_is_valid ✅ 424ms
tests/common/config_test.py::TestConfig::test_default_workflow ✅ 88ms
tests/common/config_test.py::TestConfig::test_load_default_config ✅ 3.2s
tests/common/config_test.py::TestConfig::test_max_token_len_per_gpu_set_correctly ✅ 90ms
tests/common/config_test.py::TestConfig::test_optimizer_config_propagation ✅ 88ms
tests/common/config_test.py::TestConfig::test_update_config_from_ray_cluster ✅ 1.9s
tests/common/experience_test.py::TestEID::test_eid_properties ✅ 1ms
tests/common/experience_test.py::TestExperience::test_action_mask_and_logprobs_type ✅ 1ms
tests/common/experience_test.py::TestExperience::test_assertions ✅ 1ms
tests/common/experience_test.py::TestExperience::test_dpo_experience ✅ 1ms
tests/common/experience_test.py::TestExperience::test_gather ✅ 1ms
tests/common/experience_test.py::TestExperience::test_hf_datasets_conversion ✅ 15ms
tests/common/experience_test.py::TestExperience::test_multi_turn_experience ✅ 1ms
tests/common/experience_test.py::TestExperience::test_serialize_deserialize ✅ 2ms
tests/common/experience_test.py::TestExperience::test_single_turn_experience ✅ 1ms
tests/common/experience_test.py::TestExperience::test_to_dict ✅ 1ms
tests/common/experience_test.py::TestExperienceConversion::test_batch_conversion ✅ 1ms
tests/common/experience_test.py::TestExperienceConversion::test_dpo_experience_batch_conversion ✅ 1ms
tests/common/experience_test.py::TestExperienceConversion::test_experience_model_experience_conversion ✅ 1ms
tests/common/experience_test.py::TestExperienceConversion::test_gather_experiences_with_custom_fields ✅ 1ms
tests/common/experience_test.py::TestExperienceConversion::test_multiturn_experience_batch_converstion ✅ 1ms
tests/common/vllm_test.py::ModelWrapperTest_0::test_generate ✅ 52.7s
tests/common/vllm_test.py::ModelWrapperTest_1::test_generate ✅ 31.4s
tests/common/vllm_test.py::ModelWrapperTest_2::test_generate ✅ 44.3s
tests/common/vllm_test.py::TestModelLen_0::test_model_len ✅ 17.5s
tests/common/vllm_test.py::TestModelLen_1::test_model_len ✅ 17.2s
tests/common/vllm_test.py::TestAPIServer::test_api ✅ 22.4s
tests/common/vllm_test.py::TestAsyncAPIServer::test_api_async ✅ 22.5s
tests/common/vllm_test.py::TestTokenizer::test_action_mask ✅ 238ms
tests/common/vllm_test.py::TestTokenizer::test_action_mask_with_tools ✅ 243ms
tests/common/vllm_test.py::TestAPIServerToolCall_0_deepseek_r1::test_api_tool_calls ✅ 19.5s
tests/common/vllm_test.py::TestAPIServerToolCall_1::test_api_tool_calls ✅ 18.0s

Github Test Reporter by CTRF 💚

@pan-x-c pan-x-c merged commit aa32213 into modelscope:main Nov 4, 2025
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@pan-x-c pan-x-c pan-x-c approved these changes

+1 more reviewer

@gemini-code-assist gemini-code-assist[bot] gemini-code-assist[bot] left review comments

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@hiyuchang @pan-x-c