Lightning-AI / Lightning-AI/lit-llama

[question] error message while finetuning

Open
#460 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
6.1k
Forks
517
PR merge metrics
No merged PRs in 30d

Description

Dear all,
I ran finetuning and while validating, I encountered this error message:
iter 3198: loss nan, time: 123.08ms
Validating ...
.......
lit-llama/generate.py", line 74, in generate
idx_next = torch.multinomial(probs, num_samples=1).to(dtype=dtype)
RuntimeError: probability tensor contains either `inf`, `nan` or element < 0

Could you tell me how I can solve this problem?

Thanks in advance.

Contributor guide

No contributing guide indexed for this repository

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 with the traceback in lit-llama/generate.py at line 74 and review the finetuning and validation setup that produces the NaN loss at iteration 3198. Reproduce the validation failure and identify the configuration or input causing invalid probabilities before defining a targeted fix.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.