How should I interpret training loss/metrics in encodec training

facebookresearch / audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

MIT License

20.23k stars 2.03k forks source link

How should I interpret training loss/metrics in encodec training #284

Open jasonppy opened 9 months ago

jasonppy commented 9 months ago

Hi,

Thanks for making everything open sourced.

I'm trying to train encodec model on my own data, but I'm not sure how to interpret the metrics, plus a lot of them seems to be some kinda loss but they are increasing during training, Any advice?

Thanks!