srm.git/scripts/train_srm.py, branch main Unnamed repository; edit this file 'description' to name the repository. Add SRM training pipeline 2026-05-23T09:56:47+00:00 YurenHao0426 Blackhao0426@gmail.com 2026-05-23T09:56:47+00:00 152821462023690df5d2bf90812e1cb5b1ca7274 - config/arch/srm_v1.yaml: arch config for pretrain.py integration - scripts/train_srm.py: standalone from-scratch trainer based on step4 (HRM training infra adapted for SRM joint operator) The arch.yaml exposes κ, η, α, n_iters, n_aol_layers as Hydra params. train_srm.py adds joint Lyapunov diagnostic via JVP on srm_block to verify λ_1 ≤ log((1-α)+α·κ) per micro-step. Smoke tested with hidden=128, n_iters=4 on Sudoku 1k: empirical Lip 0.28 << bound 0.90. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com> 
- config/arch/srm_v1.yaml: arch config for pretrain.py integration
- scripts/train_srm.py: standalone from-scratch trainer based on step4
  (HRM training infra adapted for SRM joint operator)

The arch.yaml exposes κ, η, α, n_iters, n_aol_layers as Hydra params.

train_srm.py adds joint Lyapunov diagnostic via JVP on srm_block to verify
λ_1 ≤ log((1-α)+α·κ) per micro-step. Smoke tested with hidden=128, n_iters=4
on Sudoku 1k: empirical Lip 0.28 << bound 0.90.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>