deepspeedai / deepspeedai/DeepSpeedExamples
step3 answer is not correct
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 6.8k
- Forks
- 1.1k
- Avg merge
- 2d 16h
- Merged PRs (30d)
- 1
Description
setting as follow:
disable HE (HE + zero2 occur error)
pp_epochs=1
num_train_epochs=1
disable_actor_dropout
per_device_train_batch_size and per_device_mini_train_batch_size are 2
actor loss
inference demo：
while actor_ema seems normal but it's effect is same with sft model
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 the step3 training and inference demo referenced in the report, using the listed HE, zero2, epoch, dropout, and batch-size settings. Compare the actor loss, actor_ema behavior, and SFT-model output shown in the screenshots, then establish what the expected step3 answer should be and why actor_ema has the same effect as the SFT model.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100