# Evidence: Masked language modeling: predict hidden tokens

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

## Evidence required

Keep corrupted inputs, selected-target counts, the log-vocabulary baseline, independent masked-loss checks, trained parameters and changed-mask results.

- Command: `python3 phases/17-pretraining/01-mlm/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