lr, rank, betas, eps, weight_decay, warmup_steps, scale, proj_refresh, norm_growth_limit — all optional with sensible defaults. Co-Authored-By: Proof of Concept <poc@bcachefs.org> |
||
|---|---|---|
| .. | ||
| apollo_plugin | ||
| research | ||
| DESIGN.md | ||
| pyproject.toml | ||
lr, rank, betas, eps, weight_decay, warmup_steps, scale, proj_refresh, norm_growth_limit — all optional with sensible defaults. Co-Authored-By: Proof of Concept <poc@bcachefs.org> |
||
|---|---|---|
| .. | ||
| apollo_plugin | ||
| research | ||
| DESIGN.md | ||
| pyproject.toml | ||