Fix metrics in trainer

[chenyushuo]

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]

Summary of Changes

Hello @chenyushuo, 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 focuses on enhancing the metric collection and reporting capabilities within the training and sampling components. The changes aim to provide more detailed insights into the training process, including model version distribution in sampled data, accurate synchronization timing, and improved task identification, ultimately leading to better monitoring and analysis of the training pipeline's performance.

Highlights

• Metric Collection for Sampled Data: Introduced a mechanism to gather and report metrics related to the model versions present in sampled experiences, providing insight into the data distribution from different model iterations.
• Refined Trainer Metric Handling: Restructured how metrics are collected within the Trainer's main loop, ensuring that metrics from sync_weight and _sample_data are properly aggregated and reported.
• Improved Synchronization Interval Tracking: Added a new metric, time/trainer_sync_interval, to accurately measure the duration between consecutive weight synchronizations, providing better visibility into synchronization overhead.
• Enhanced Task Identification in Samples: Modified the calculation of sample/task_count to include both batch and task IDs, ensuring more unique and granular identification of tasks within sampled data.

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]

Code Review

This pull request refactors how metrics are calculated in the trainer, particularly improving the accuracy of timing metrics like trainer_sync_interval. It also introduces a new metric for tracking model versions of sampled experiences and fixes a bug in counting unique tasks. The changes are generally positive. I've identified one potential runtime error that could cause a crash and a minor opportunity for code simplification, which are detailed in the comments.

[pan-x-c]

/unittest-module-algorithm

[github-actions]

Summary

Tests 📝	Passed ✅	Failed ❌	Skipped ⏭️	Other ❓	Flaky 🍂	Duration ⏱️
14	14	0	0	0	0	11.1s

Tests

Test Name	Status	Flaky	Duration
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_batch_level_std_grpo	✅		41ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_batch_level_step_wise_grpo_advantage	✅		2ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_duplicate_grpo	✅		5ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_advantage	✅		3ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_correct_bias	✅		2ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_grpo_reward_std	✅		1ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_step_wise_grpo_advantage	✅		2ms
tests/algorithm/advantage_fn_test.py::TestGroupedAdvantageFn::test_step_wise_grpo_with_std_threshold	✅		2ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_dpo_policy_loss	✅		2ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_gspo_policy_loss	✅		1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_mix_policy_loss	✅		1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_opmd_policy_loss	✅		1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_ppo_policy_loss	✅		1ms
tests/algorithm/policy_loss_test.py::VerlPolicyLossTest::test_sft_policy_loss	✅		1ms

Github Test Reporter by CTRF 💚