JinghuaiZzz

icon indicating an email [email protected]

icon location Los Angeles icon location ECE PhD student at UCLA.

Results 3 issues of JinghuaiZzz

Loss problem

I use my own caffe and find the loss doesn't decrease a lot. After a period of training, nan happens. The data layer is same as predict process provided by...

training loss increases and keeps near 3.26+07 in my own dataset

I clone the git, install the PSP net version caffe, and also download the pretrained model. After I change the path to my own dataset, I use the bash code:...

[Question]: Fail to reproduce llmlingua on meetingbank

1 comment

### Describe the issue Thanks for the interesting work. I tried to reproduce the results of llmlingua on the meetingbank QA dataset with Mistral-7B as the target LLM. The small...

question