PR openai#462 base (1.0672 SOTA) + novel 25-epoch quant-sensitivity TTT

Base: PR openai#462's SwiGLU + XSA4 + U-Net architecture (1.0672 BPB)
Novel additions (untried combination):
1. 25 TTT epochs (up from 10) - loss still dropping at epoch 10
2. Per-layer TTT LR by quantization sensitivity:
   - MLP output projections: 3x LR (highest quant damage)
   - MLP input projections: 0.5x LR
   - Everything else: 1x LR
3. DDP optimize_ddp fix for PyTorch 2.4

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: het4rk