| { | |
| "backbone": "Qwen/Qwen3.5-2B-Base", | |
| "backbone_revision": "b1485b2fa6dfa1287294f269f5fb618e03d52d7c", | |
| "input_size": 2048, | |
| "hidden_size": 1024, | |
| "num_layers": 20, | |
| "num_heads": 16, | |
| "intermediate_size": 4096, | |
| "max_length": 512, | |
| "dropout": 0.1, | |
| "gradient_checkpointing": true, | |
| "pooling": "masked_mean", | |
| "categories": [ | |
| "harassment", | |
| "harassment_threatening", | |
| "hate", | |
| "hate_threatening", | |
| "self_harm", | |
| "self_harm_instructions", | |
| "self_harm_intent", | |
| "sexual", | |
| "sexual_minors", | |
| "violence", | |
| "violence_graphic" | |
| ], | |
| "training": { | |
| "epochs": 10, | |
| "batch_size": 4, | |
| "gradient_accumulation": 8, | |
| "learning_rate": 0.0001, | |
| "weight_decay": 0.01, | |
| "warmup_fraction": 0.05, | |
| "max_grad_norm": 1.0, | |
| "early_stopping_patience": 3, | |
| "dtype": "bfloat16", | |
| "seed": 20261003, | |
| "loss": "BCEWithLogitsLoss with original soft scores", | |
| "cuda_memory_fraction": 0.40875889995586007 | |
| }, | |
| "calibration": { | |
| "status": "fitted_internal_only", | |
| "file": "calibration/thresholds.json", | |
| "probabilities_calibrated": false | |
| }, | |
| "checkpoint_epoch": 5 | |
| } |