Add QK-norm toggle, TinyStories prep and automatic run logging

nanoGPT gets a qk_norm flag (off = upstream behaviour), a seed option and
a resolved-config dump. run.py logs each run's git commit, config, data
checksums, environment and metrics, and stops diverged runs.

Claude-Session: https://claude.ai/code/session_01S8KN7NuUCm8nXLmy6eDuVv

.gitignore

@@ -29,7 +29,7 @@ __pycache__/
 .venv/
 
 # Experiment data, checkpoints and raw outputs (run metadata in runs/ IS tracked)
-06-experiments/data/
+06-experiments/data/*/
 06-experiments/vendor/
 06-experiments/runs/*/ckpt.pt
 06-experiments/runs/*/stdout.log