model:
  name: "/root/siton-data-2849d4ce327c4ccfb233ce33868fe7fe/zsy/macbert-large"
  hidden_size: 1024
  num_heads: 8
  dropout: 0.1
  use_lora: false

data:
  train_path: "data/processed/CompanionRisk-Bench/train.jsonl"
  val_path:   "data/processed/CompanionRisk-Bench/dev.jsonl"
  test_path:  "data/processed/CompanionRisk-Bench/test.jsonl"
  max_persona_len:   128
  max_context_len:   512
  max_response_len:  256
  max_history_turns: 5
  num_workers: 4
  ablation_mode: "response_only"   # 消融：仅 Response 流，persona/context 均置空

training:
  epochs: 10
  per_gpu_batch_size: 16
  gradient_accumulation_steps: 2
  lr: 2e-5
  warmup_steps: 100
  weight_decay: 0.01
  gradient_clip: 1.0
  eval_steps: 100
  mixed_precision: "bf16"
  seed: 42

loss_weights:
  binary:  1.0
  level:   1.0
  primary: 1.0
  fine:    2.0

fine_training:
  use_pos_weight: true
  risky_only:     true

evaluation:
  binary_threshold: 0.5
  fine_threshold:   0.4

logging:
  project:   "CompanionGuard-RL"
  run_name:  "detector-abl-response-only"
  use_wandb: false

output:
  checkpoint_dir: "checkpoints/detector_abl_response_only"