v0.2.1
What's changed: DX Improvements by @thetianshuhuang in #21
Improvements to the developer experience:
- Better logging & error messages
- Only write high-level log messages from rank 0 in multi-GPU training to avoid cluttering the log
- Better looking outputs using rich trees for
nrdk inspect - Log gradient norm in
NRDKLightningModule
Other fixes:
- Only write
checkpoints.yamlfrom rank 0 to prevent concurrency bugs - Freeze models loaded with
framework.load_modelby default - Fix
@cache @torch.compiler.disableordering
Full Changelog: v0.2.0...v0.2.1