deepspeedai / deepspeedai/DeepSpeedExamples
use bloom-350m to train reward model in step2
Open
Nobody has claimed this yet.
deespeed chat
new-config
- Dominant language
- Python
- Stars
- 6.8k
- Forks
- 1.1k
- Avg merge
- 2d 16h
- Merged PRs (30d)
- 1
Description
I want to train bloom_350m in chinese dataset, and run run_350m.sh, change the model_name_or_path. But the loss is nan, how should I solve it? Is the argument "num_padding_at_beginning" cause this?
Contributor guide
No contributing guide indexed for this repository
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
Start with run_350m.sh and the step2 training path, then reproduce the NaN loss using the Chinese dataset and BLOOM-350M model path. Inspect how num_padding_at_beginning is passed and identify whether it causes the failure; done means a confirmed cause and a documented corrective change or configuration.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, shell
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100