Tony Jiang

Gotcha, thanks! @zjysteven, a follow up question. Is it possible to finetune using Lora and do further lora finetuning on top of that already finetuned model? If so, how would...

thanks @zjysteven I actually tried that, doing further training on top of an already finetuned model by providing the checkpoint. The issue arises after the second training is complete and...

@zjysteven I need to test again to make sure, but what I mean by "collapsed" is that the final model started to return gibberish. The secondary finetuning I am trying...

Hi @zjysteven just a qq and again thanks for this amazing work. Can we save a checkpoint for each epoch or base on how many steps? I did ran into...

@LaBaZh I would love to see that as well. Where can I see that? Thanks in advance.

@GohioAC were you able to resolve it? I got a similar issue.

thanks, I updated to the latest dev version of transforms but still ran into the issue. Could you shed more light why it occurs? I am trying to reproduce this...

@qgallouedec Hmmm, I believe this tutorial notebook (https://colab.research.google.com/drive/1dTdro-k7NFqRgGq5-TlGHM-6k2sYQhXp?usp=sharing#scrollTo=5da82ca2-e1db-4a7c-878f-aeed972ba9e6) on LLaVA-Next-Video finetuning was made by a member of the LLaVA Hugging Face team member, Raushan Turganbay... not sure if you know....

Thanks it's not, i didn't know this is specific to TRL. @qgallouedec @zuchini-nlp any help on this error for notebook would be much appreciated! @zucchini-nlp any pointers on the library...

hey @zucchini-nlp thanks for replying. I made sure i am using the latest patch release 4.44.2 and ran the notebook but still got into the following error when I tried...