Dropout / unsupervised training implementation ?
Natooz opened this issue Β· comments
Hello, π
First thank you for the very good quality of your code and the support you gave to issues / PR.
For a research projet, I am fine-tuning models on a contrastive objective. I intend to use your unsupervised method.
Looking at the code of SimCSE, I noticed that in the forward pass all sequences
My workaround is to perform two forward passes through the BERT encoder, but I still wondered, did you do the same or maybe am I missing something ?