docs: v3.2.0 changelog

Author: kozistr

docs/changelogs/v3.2.0.md

@@ -10,6 +10,7 @@
     * `torchao_adamw8bit`, `torchao_adamw4bit`, `torchao_adamwfp8`.
 * Support a module-name-level (e.g. `LayerNorm`) weight decay exclusion for `get_optimizer_parameters`. (#282, #283)
 * Implement `CPUOffloadOptimizer`, which offloads optimizer to CPU for single-GPU training. (#284)
+* Support a regex-based filter for searching name of optimizers, lr schedulers, and loss functions. (#285)
 
 ### Bug