Merge nucleic/sleek-ember-seal-uady into dev

README.md

@@ -326,6 +326,30 @@ expected to be extremely slow there. Each improved epoch atomically rewrites `mo
 and updates `training-state.json`, so progress is visible and an interrupted run retains
 the last selected checkpoint.
 
+To continue a completed run without discarding its trained task heads, pass its selected
+`model/` directory through `--resume-from` and write to a new output directory.
+Continuation restores the backbone and all four heads strictly, then starts a fresh
+optimizer and learning-rate schedule; `--model` remains reserved for an untrained local
+upstream checkpoint. The first base run was still improving when its three-epoch schedule
+ended, so continue its selected checkpoint conservatively before changing architecture:
+
+```bash
+ml/purpose-classifier/venv/bin/python -u \
+  ml/purpose-classifier/train_deep_mlx.py \
+  --variant base \
+  --resume-from \
+    ml/purpose-classifier/outputs/purpose-deep-v1-base-mlx/model \
+  --dataset-dir \
+    ml/purpose-classifier/.artifacts/dataset-v1-history-first-prompts \
+  --epochs 3 \
+  --learning-rate 1e-5 \
+  --early-stopping-patience 2 \
+  --progress-steps 10 \
+  --output-dir \
+    ml/purpose-classifier/outputs/purpose-deep-v1-base-mlx-cont-3e \
+  --overwrite-output
+```
+
 Do not launch the large rung yet. It is justified only after base is evaluated on the
 frozen set; large must beat base by at least two hard-slice points, while deep itself must
 reach 97% scored overall and beat the shipping lite artifact by five hard-slice points.