verl-project/verl

[FR] Better metric reduction utility

Open

#1,508 建立於 2025年5月13日

在 GitHub 查看
 (2 留言) (2 反應) (0 負責人)Python (21,533 star) (3,940 fork)auto 404
enhancementfeature requestgood first issue

描述

Motivation

reduce_metrics seems to be used for reducing metrics across DP ranks and batches, which only simply means the values.

However, reducing metrics across DP ranks is non-trivial since some metrics like "mean" are not linear.

貢獻者指南

技術棧
pythonpytorch
領域
machine learningdata
議題類型
feature
難度面向新貢獻者的預計實作難度，1 表示很小改動，5 表示專家級工作。
4
預計時間有經驗貢獻者完成調查、實作、測試並準備 pull request 的粗略時間範圍。
1-2 days
活動狀態議題目前的可參與程度：新鮮、活躍、陳舊、阻塞或等待維護者輸入。
fresh
清晰度議題是否清楚說明預期改動、驗收標準和下一步。
mostly clear
前置要求
PythonPyTorch distributedverl codebase
新手友善度1-100 的估計分數，表示該議題對首次貢獻者的友善程度。
25
研究方向
Investigate the current reduce metrics function at https://github.com/verl project/verl/blob/main/verl/utils/metric/utils.py. Understand the different types of metrics and their reduction requirements across data parallel ranks. Propose a generalized reduction strategy that accounts for non linear metrics like mean. Consider existing implementations in PyTorch or other frameworks.
[FR] Better metric reduction utility · verl-project/verl#1508 | Good First Issue