Kaizhi Qian

Right. All these lengths are hyperparameters that can be freely adjusted based your own requirements.

@jixinya Yes, the validation data is just a separate partition of the training data.

This repo does not include the code for training.

Sounds like overfitting.

The structure of the validation set does not matter. Just make sure the input to the model is correct.

Yes. Same as training

@AShoydokova 1. Your training set may be too small. 2. validation setup should be consistent with training

batch size cannot be larger than the data size

It might be due to the content loss in the content embedding. Maybe you could try replacing the SEA with a better self-supervised model.

The model should be easy to train. I don't know what exactly is the problem by looking at the picture.