r03922123

The discussion https://github.com/facebookresearch/audiocraft/issues/267 explains that default checkpoint is saved as best checkpoint based on validation metric, could we set any configuration to get last checkpoint without considering validation metric? Thank...

Thank you all for making this project public! When I try to do train_test_split of my custom dataset (it's a small dataset, less than 2000 samples), I am thinking about...

I am curious about how "grad_accum_every" used in https://github.com/lucidrains/musiclm-pytorch/blob/main/musiclm_pytorch/trainer.py#L317 In my previous experience, the model basically get gradient (backward) once a step. Why should we split loss "grad_accum_every" times to...