Load from correct self.steps to resume training

lucidrains / audiolm-pytorch

Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch

MIT License

2.33k stars 249 forks source link

Closed LWprogramming closed 1 year ago

LWprogramming commented 1 year ago

So it doesn't start from 0 when loading from checkpoint

lucidrains commented 1 year ago

love it! thanks!