4B matched control (fixed-normal prior, identical SFT+RL recipe to hidden); folded LoRA, step 400
8c686c6 verified | { | |
| "_from_model_config": true, | |
| "eos_token_id": 248044, | |
| "transformers_version": "5.3.0", | |
| "use_cache": true | |
| } | |
| { | |
| "_from_model_config": true, | |
| "eos_token_id": 248044, | |
| "transformers_version": "5.3.0", | |
| "use_cache": true | |
| } | |