Ghazal Sahebzamani

I used to have the same issue and I figured it was because I was using hugging face's "llava-hf/llava-1.5-7b-hf" as the base model. I switched the base to "liuhaotian/llava-v1.5-7b" and...

Facing the same issue here. The output is nan although my w&B loss looks fine.

Update: I was able to resolve the issue by changing the base model from hugging face's "llava-hf/llava-1.5-7b-hf"to "liuhaotian/llava-v1.5-7b". It resolved the NaN issue and the training performance got much better.

I have been facing the same issue.

Update: I was able to resolve the issue by changing the base model from hugging face's "llava-hf/llava-1.5-7b-hf"to "liuhaotian/llava-v1.5-7b". It resolved the NaN issue and the training performance got much better.