diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-01 12:56:24 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-01 12:56:24 -0500 |
| commit | d5326053a2e9ce37dd61606aa37fa8f563481f44 (patch) | |
| tree | 653f8bf3098d382a1162c09ce4983d9d1c50713e /metrics/__init__.py | |
| parent | cd80da41c620d7c8b17e36d3ed7ab7e6b582f191 (diff) | |
Add clean gradient check: independent Python process per method, GPU 1
Clean results (each method in fresh Python process):
BP: mean_norm=2.58e-04, s(1e-6)=98% — CONFIRMED
DFA: layer 0 = 2.86e-07 (1.2%), layers 1-3 ≈ 2.4e-09 (0%)
SB: layer 0 = 6.13e-06 (86%), layers 1-3 ≈ 1e-09 (0%)
CB: layer 0 = 6.33e-07 (18%), layers 1-3 ≈ 5e-10 (0%)
Method A (autograd.grad) and Method B (retain_grad) give identical results.
Previous 1e-12 results were caused by Python process state pollution in combined scripts.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'metrics/__init__.py')
0 files changed, 0 insertions, 0 deletions