# Modello addestrato: submission_dpo_from_validator
- Data: 2025-07-09T21:58:08.998726
- Epochs: 2
- Learning Rate: 1e-4
- LoRA config: r=64, q=128

SHA256 del modello (model.safetensors):
238bf8909c1d373d93571890b67438ec1130ea05edd2f0a3556feba865061107