Exact reproduction of all 7 CL-BPL phases for Gemma3-12B:
- P0: LEK sandwich ethics (400 iters, LR 2e-5)
- P1: Zen composure (300 iters, LR 1e-5)
- P2: LEK sandwich reinforcement (300 iters, LR 1e-5)
- P3: Freeflow multi-source (300 iters, LR 1e-5)
- P4: 1B teacher tension distillation (300 iters, LR 1e-5)
- P5: 1B teacher creative distillation (300 iters, LR 1e-5)
- P6: Golden set graduation (13479 iters, LR 1e-5)
Only model-size differences from 4B: 48GB/12GB Metal limits,
24 LoRA layers (vs 16), 12B base model path.
All phases score at checkpoint cadence via lem-scorer.
Previous wrong 12B models preserved as -no-axioms control group.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
CacheLimit (8GB) and MemoryLimit (16GB) in DistillConfig control
mlx.SetCacheLimit/SetMemoryLimit before model load. Conservative
defaults for 1B model on 96GB machine.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Move training/lem/ (probes, lessons, eval sets) into git so the
full curriculum is publicly releasable. Update .core/ai configs
and distill.go to use repo-relative paths instead of /Volumes/Data/.
Co-Authored-By: Virgil <virgil@lethean.io>
