# Evidence: Masking, tokenization, and sequence packing

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

## Evidence required

Keep token/target alignment, the two masks, future perturbation, segment-leakage comparison and all-masked-row repair. Verify that masks and ignored loss positions enforce the same boundaries.

- Command: `python3 phases/07-transformers/02-masking-tokenization-and-sequence-packing/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