# Evidence: RLHF mechanics: a frozen reward and PPO policy updates

Copy this template into your own portfolio and fill it after running your modified exercise.

## Evidence required

Keep reward/reference identity, collected old probabilities, signed clipping checks, exact reward/KL history and detached behavior information.

- Command: `python3 phases/18-posttraining/04-rlhf/code/main.py`
- Working directory: repository root
- Python / JAX / NumPy versions: 
- Hardware and device: 
- My prediction before running: 
- My change to the exercise: 
- Exit code and meaningful output: 
- Why the result supports or contradicts my prediction: 
- Checkpoint result: 
- Artifact link or saved filename: 
- Portfolio status: saved in local workspace