Zero Training Loss while finetuning the model for summarization

#14
by Praful932 - opened

Thanks for your work!

I am trying to finetune this model using LORA for summarization, but unable to get it to work, I have shared more details here in the github issue - https://github.com/huggingface/trl/issues/1225

the issue was resolved

Praful932 changed discussion status to closed

Sign up or log in to comment