diff options
| -rw-r--r-- | prime-grokking/main.md | 15 |
1 files changed, 15 insertions, 0 deletions
diff --git a/prime-grokking/main.md b/prime-grokking/main.md index 863543c..257b235 100644 --- a/prime-grokking/main.md +++ b/prime-grokking/main.md @@ -138,3 +138,18 @@ cross the gap from pattern matching to computation. used the old `[101,200]` probe, so E6's locked probe was run separately on CPU. E7 remains the planned 4M-step (20×) follow-up on the strongest E6 cells, to distinguish a slow generalising basin from its absence. + +### 2026-08-18 — E6 complete + +- All 16 pre-registered CUDA/AMP cells are complete. No O1, P5(k), or P6 + outcome occurred: seven low-weight-decay cells are O-PARTIAL, nine are O4, + and every cell is P4 on the locked `[1001,2000]` probe. The wd=1.0 three-seed + replication is O4 in both architectures. +- Thus the 10× range extension improved in-range fitting but did not yield a + transferable sieve/divisibility signature; E6 supports an algorithmic rather + than data-bound wall. The batch-128 transformer was additionally unstable at + the end of training (train EM 1.00→0.55; val EM 0.83→0.45). +- The E7 4M-step follow-up remains the discriminating test for a slow basin. + 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. |