# Evidence: Train a CNN on a small dataset

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

## Evidence required

Keep the 8-by-8-to-6-by-6 shape diagram, NumPy patch dot product, seeds 20/21, independent held-out cross-entropy, 24-observation confusion matrix, constant-class baseline, and layout failure repair.

- Command: `python3 phases/05-networks/04-train-a-cnn-on-a-small-dataset/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