diff options
Diffstat (limited to 'MIXED_TRAFFIC.md')
| -rw-r--r-- | MIXED_TRAFFIC.md | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/MIXED_TRAFFIC.md b/MIXED_TRAFFIC.md index 0f14e05..4852ef0 100644 --- a/MIXED_TRAFFIC.md +++ b/MIXED_TRAFFIC.md @@ -119,6 +119,16 @@ The accuracy gaps and same-state alignment rotation are conjunctive: clipping an unstable raw update is not enough. MT-1 failure closes the branch without a weaker traffic ratio. A pass opens MT-2 but leaves the reviewer score at 5/10. +MT-1 fails. All three clean-revision records become nonfinite during epoch 1 +and end at 10.00% validation accuracy with NaN loss. Thus innovation does not +separate from either raw control at the frozen four-to-one intervention. The +initial layer-ratio error is only `4.77e-7`, neutral warmup leaves a traffic +residual ratio of `0.139942`, all conditions use zero task-loss queries, and +each costs `1.3271x` the epoch-20 BP MAC reference. Calibration, warmup, query, +and cost invariants therefore pass, but they do not rescue the failed finite, +accuracy, alignment, tracking, or norm checks. MT-2 and MT-3 remain untouched; +the branch closes without changing traffic strength or predictor schedule. + ## MT-2: frozen full validation gate Copy MT-1 exactly for 200 epochs. The three jobs remain seed 0 and do not touch |