diff options
Diffstat (limited to 'prime-grokking')
| -rw-r--r-- | prime-grokking/main.md | 17 |
1 files changed, 17 insertions, 0 deletions
diff --git a/prime-grokking/main.md b/prime-grokking/main.md index 257b235..a677fa5 100644 --- a/prime-grokking/main.md +++ b/prime-grokking/main.md @@ -153,3 +153,20 @@ cross the gap from pattern matching to computation. Before it, `src/eval.py` must implement the locked `[1001,2000]` probe and P5/P6 ladder: its stored P fields still derive from the obsolete `[101,200]` evaluation. + +### 2026-08-21 — E7 long-horizon protocol locked + +- E7 is pre-registered as the direct duration test: four E6-derived cells + (`wd={0.1,0.3}` × tied RNN/transformer, seed 0) extend only the training + horizon from 200k to 4M steps. An O1 transition would make the prior nulls + budget-limited; unchanged O-PARTIAL/O4 with no P5/P6 signature would make + the E6 negative result robust to a 20× budget increase. +- The protocol preserves E6's `[2,1000]` digits task, K=32, and train split. + RNN runs on ichi CPU (the sequential tied cell benchmarked faster there); + transformer runs AMP/compiled on the T1000. Adaptive evaluation reduces + monitoring overhead without changing the training objective. +- This test is motivated by the original grokking result's delayed + generalization: small datasets can require far more optimization after + overfitting. It does not assume primes have a simple closed-form pattern; + the bounded target remains a test of whether a learned trial-division + procedure can beat memorization. |