Merge pull request #307 from kozistr/release/v3.3.0

[Release] v3.3.0

Author: kozistr

docs/changelogs/v3.3.0.md

@@ -14,6 +14,14 @@
 * Improve the stability of `ADOPT` optimizer. (#294)
     * [Note](https://github.com/iShohei220/adopt?tab=readme-ov-file#update-on-nov-22-2024) 
 * Support a new projection type `random` for `GaLoreProjector`. (#294)
+* Implement `DeMo` optimizer. (#300, #301)
+    * [Decoupled Momentum Optimization](https://arxiv.org/abs/2411.19870)
+* Implement `Muon` optimizer. (#302)
+    * [MomentUm Orthogonalized by Newton-schulz](https://github.com/KellerJordan/Muon)
+* Implement `ScheduleFreeRAdam` optimizer. (#304)
+* Implement `LaProp` optimizer. (#304)
+    * [Separating Momentum and Adaptivity in Adam](https://arxiv.org/abs/2002.04839)
+* Support `Cautious` variant to `LaProp`, `AdamP`, `Adopt` optimizers. (#304).
 
 ### Refactor
 

docs/changelogs/v3.3.1.md

@@ -2,11 +2,3 @@
 
 ### Feature
 
-* Implement `DeMo` optimizer. (#300, #301)
-    * [Decoupled Momentum Optimization](https://arxiv.org/abs/2411.19870)
-* Implement `Muon` optimizer. (#302)
-    * [MomentUm Orthogonalized by Newton-schulz](https://github.com/KellerJordan/Muon)
-* Implement `ScheduleFreeRAdam` optimizer. (#304)
-* Implement `LaProp` optimizer. (#304)
-    * [Separating Momentum and Adaptivity in Adam](https://arxiv.org/abs/2002.04839)
-* Support `Cautious` variant to `LaProp`, `AdamP`, `Adopt` optimizers. (#304).