EuroSafeGuard v1: probe, 5 input-classifier seeds, exchange classifier, thresholds, loader, model card
b8ee2d2 verified | { | |
| "model_name": "Qwen/Qwen3.5-9B", | |
| "objective": "multilabel", | |
| "balanced_sampling": false, | |
| "num_labels": 11, | |
| "borderline_benign_target": 0.5, | |
| "dual_use_harmful_target": 0.8, | |
| "lora_r": 128, | |
| "lora_alpha": 256, | |
| "lora_dropout": 0.0456, | |
| "lora_target_modules": null, | |
| "lr": 0.0002, | |
| "lr_backbone": 5.29e-05, | |
| "lr_head": 0.00012, | |
| "max_steps": 24000, | |
| "batch_size": 4, | |
| "max_grad_norm": 1.0, | |
| "compile": false, | |
| "seed": 2, | |
| "max_length": 1024, | |
| "dataset_loop": true, | |
| "dataset_text_column": "prompt", | |
| "dataset_category_column": "category", | |
| "dataset_entry_type_column": "entry_type", | |
| "dataset_method_column": null, | |
| "dataset_split": "train", | |
| "sample_categories": null, | |
| "sample_complexity": 1, | |
| "eval_frac": 0.02, | |
| "eval_every": 2000, | |
| "table_every": 500, | |
| "moving_avg_window": 100, | |
| "save_every": 12000 | |
| } |