diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-08 13:21:19 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-08 13:21:19 -0500 |
| commit | 4ec8d0d9516d2c134df26ec4781d5e7fc63dedbd (patch) | |
| tree | fb85cac1f1941a4ef6b1c7408c8129f679ceffd1 /results/ep_baseline/ep_s42.json | |
| parent | 3919f5a7db4abb699af150107bb1a2c587c14cfd (diff) | |
Round 41 (Appendix L): add 4th piece of cos-vs-acc evidence - trajectory loss decrease
SB+penalty train loss: 2.047 -> 1.589 (Δ=0.458 over 30 epochs)
CB+penalty train loss: 1.996 -> 1.874 (Δ=0.122 over 30 epochs)
Ratio: 3.8x (matching the 4x nudging ratio)
This is the third independent functional measurement, from per-epoch logs
in the same round 38 JSONs (log['train_loss']). The cos-vs-acc
dissociation now has four independent pieces of evidence, all agreeing:
1. Test accuracy: CB 0.360 vs SB 0.453 (9.3pp gap)
2. Parameter drift: CB w2 19.3x vs SB 14.3x (CB larger updates)
3. Single-step nudging Δloss: CB -0.45e-3 vs SB -1.78e-3 (4x gap, eta=0.01)
4. Trajectory loss decrease: CB 0.122 vs SB 0.458 (3.8x gap over 30 epochs)
All four inversely correlated with deep cosine (CB has higher deep cos).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'results/ep_baseline/ep_s42.json')
0 files changed, 0 insertions, 0 deletions