Does finetune/run_simcse.py only support unsupervised training?

[Eric8932]

During training, the tgt of the loss function is torch.arange(batch_size), which is suitable for unsupervised training. But this will overwrite the labels of the supervised training set.

[ydli-ai]

For now, we only implemented the unsupervised part of simcse. If you are interested, you can contribute your code and open a PR.