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            # Linux server: 4 workers; Windows: use 0

training:
  epochs: 10
  per_gpu_batch_size: 16    # 4 GPUs × 16 × accum 2 = effective batch 128
  gradient_accumulation_steps: 2
  lr: 2e-5
  warmup_steps: 100
  weight_decay: 0.01
  gradient_clip: 1.0
  eval_steps: 100           # global steps between validation runs
  mixed_precision: "bf16"   # RTX 5090 native bf16
  seed: 42

loss_weights:
  binary:  1.0
  level:   1.0
  primary: 1.0
  fine:    2.0     # ↑ 2.0: 加强细粒度标签损失权重（配合 fine_training 开启）

# Fine-grained label training options（下次训练时开启，当前 best.pt 不受影响）
# 两项均开启可显著改善 fine_macro_f1：
#   use_pos_weight: 对 Romanticization/CoRumination 等稀有标签设置 ~25 倍正样本权重
#   risky_only:     只在 y_risk=1 的样本上计算 fine loss，避免 safe 样本教模型预测全负
fine_training:
  use_pos_weight: true    # ✓ 开启：对稀有 fine 标签设置 pos_weight（max 30）
  risky_only:     true    # ✓ 开启：只在 y_risk=1 样本上计算 fine loss

evaluation:
  binary_threshold: 0.5
  fine_threshold:   0.4

logging:
  project:   "CompanionGuard-RL"
  run_name:  "detector-macbert-4gpu"
  use_wandb: false

output:
  checkpoint_dir: "checkpoints/detector"