lock model

src/README.md

@@ -1,5 +1,30 @@
 # Running Notebooks in Background
 
+## Quick: Check Ray Tune Progress
+
+**Current run:** PaddleOCR hyperparameter optimization via Ray Tune + Optuna.
+- 64 trials searching for optimal detection/recognition thresholds
+- 2 CPU workers running in parallel (Docker containers on ports 8001-8002)
+- Notebook: `paddle_ocr_raytune_rest.ipynb` → `output_raytune.ipynb`
+- Results saved to: `~/ray_results/trainable_paddle_ocr_2026-01-18_17-25-43/`
+
+```bash
+# Is it still running?
+ps aux | grep papermill | grep -v grep
+
+# View live log
+tail -f papermill.log
+
+# Count completed trials (64 total)
+find ~/ray_results/trainable_paddle_ocr_2026-01-18_17-25-43/ -name "result.json" ! -empty | wc -l
+
+# Check workers are healthy
+curl -s localhost:8001/health | jq -r '.status'
+curl -s localhost:8002/health | jq -r '.status'
+```
+
+---
+
 ## Option 1: Papermill (Recommended)
 
 Runs notebooks directly without conversion.