microsoft / microsoft/SkillOpt
question about train config
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.3k
- Forks
- 1.6k
- Avg merge
- 2d 7h
- Merged PRs (30d)
- 17
Description
in config/searchqa/default.yaml，train_size is 400，epoch is 4，batch_size is 40 ,so the step is 4*（400/40）=40，but docs/guide/first_experiments.md note that searchqa train process will cost just 30 min and the stop num is 8.
So what is the real default config of searchqa?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Compare config/searchqa/default.yaml with docs/guide/first_experiments.md, focusing on train_size, epoch, batch_size, training duration, and stop num. Determine which values are the intended defaults and document one consistent configuration so the guide and config agree.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 2/5
- Estimated time
- 1-3 hours
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 50/100