THUDM / THUDM/slime

[Question] 有没有文档解释打印日志各项指标的含义

Open
#1,621 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

question
Dominant language
Python
Stars
8.5k
Forks
1.3k
Avg merge
5h 36m
Merged PRs (30d)
22

Description

Image 在做qwen2.5-3b-instruct模型在dapo-math-17k数据demo的时候,效果一直不好,然后看了下打的日志,train/loss那里非常小,我不知道这是不是正常的
What I've Tried

看了文档,没找到解释日志指标含义的内容

Environment (if relevant)
Additional Context

No response

Pre-submission Checklist

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the existing documentation and FAQ linked in the issue, then locate where the training metrics are documented or emitted. Document the meanings of the logged metrics, including train/loss, and explain how users can tell whether their values are expected; the documentation should address the reported question without requiring an issue comment.

Written by the indexing model from the issue text.

Assessment

Domain
documentation
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.