Hi, I am wondering if you freeze the pre-trained part of parameters, and only fine-tune on the downstream task with head? It seems like all parameters are tuned during the fine-tune? Thanks!
When fine-tuning VQA, all parameters are trainable. If you only want to adjust the weights of cls head, you can freeze the lxrtencoder in src/tasks/vqa_model.
Hi, I am wondering if you freeze the pre-trained part of parameters, and only fine-tune on the downstream task with head? It seems like all parameters are tuned during the fine-tune? Thanks!