| { | |
| "num_reasoning_steps": 3, | |
| "delta_target_ratio": 0.2, | |
| "lambda_coherence": 0.1, | |
| "lambda_delta_reg": 0.5, | |
| "memory_max_size": 50, | |
| "memory_retrieval_k": 3, | |
| "use_mixed_precision": false, | |
| "bypass_delta_calculation": false, | |
| "use_dynamic_steps": true, | |
| "max_reasoning_steps": 5, | |
| "min_reasoning_steps": 1, | |
| "reasoning_step_type": "learned", | |
| "early_stop_threshold": 0.01 | |
| } |