Fine-tuning LongVILA
lyluh opened this issue · 2 comments
lyluh commented
I am able to fine-tune the original models fine with the /scripts/v1_5/release/3b/3_sft.sh file using my own custom videos, but when I try to train the new LongVILA model I get this warning message and the loss is 0.0 and eval loss is NaN:
Any ideas?