Jeremy88888

'loss': 0.0 and 'grad_norm' remains the same in all steps in task lora finetuning

10

I am training task lora on "liuhaotian/llava-v1.5-13b" by following the same code in LLaVA repo: https://github.com/haotian-liu/LLaVA/blob/main/scripts/v1_5/finetune_task_lora.sh The above runs fine in LLaVA repo (https://github.com/haotian-liu/LLaVA/tree/main). When I run it in this...