Actor loss nan and Resizing model embedding
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 25/100
- Issue type
- Bug
- Clarity
- Needs clarification
- Activity status
- Stale
- Tech stack
- python
- Domain
- machine-learning
Research direction
Reproduce the GPT-2 124M training case with embedding resizing enabled for STF and RW, then inspect generated token IDs, vocabulary bounds, zero-only outputs, log probabilities, and actor loss. Compare the same training without resizing. Done means the resizing-related cause is identified and the training behavior is verified without invalid token IDs or NaN losses.
Written by the indexing model from the issue text.
Description
The model I use is GPT-2 124M. When resizing model embeddings during the training of STF and RW, I often encounter issues where the generated answers consist entirely of zeros. This causes both the log probabilities and actor loss to become NaN (Not a Number). I have noticed that resizing the embeddings can lead to the generation of token IDs that exceed the vocabulary size. I suspect this may be contributing to the problem. However, when I don't resize the model's embeddings and train STF and RW, I do not experience this issue during RLHF training. I don't know why.
- Dominant language
- Python
- Stars
- 6.8k
- Forks
- 1.1k
- Avg merge
- 2d 16h
- Merged PRs (30d)
- 1
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.
More from deepspeedai/DeepSpeedExamples
-
Difficulty 2/5 1-3 hours Newbie friendliness 52/100
deepspeedai/DeepSpeedExamples#996 ·
-
Difficulty 4/5 3-5 days Newbie friendliness 25/100
deepspeedai/DeepSpeedExamples#995 ·
-
Difficulty 2/5 1-3 hours Newbie friendliness 52/100
deepspeedai/DeepSpeedExamples#989 ·
-
moe example 404 Open
Difficulty 4/5 3-5 days Newbie friendliness 25/100
deepspeedai/DeepSpeedExamples#984 ·
-
Difficulty 4/5 3-5 days Newbie friendliness 42/100
deepspeedai/DeepSpeedExamples#979 · 6 comments ·
All issues in deepspeedai/DeepSpeedExamples
Similar issues
-
agent-ready documentation needs-triage
Difficulty 1/5 1-3 hours Newbie friendliness 88/100
-
documentation
Difficulty 1/5 Under an hour Newbie friendliness 91/100
-
workflow-status page template still says reusable workflows are "triggered only by workflow_call:" Open
Difficulty 1/5 Under an hour Newbie friendliness 92/100
-
instance instance add
Difficulty 1/5 Under an hour Newbie friendliness 72/100
searxng/searx-instances#939 · 1 comment ·
-
area-deployment area-integrations triage:bot-seen
Difficulty 2/5 Half a day Newbie friendliness 86/100