model:
  name: "hfl/chinese-macbert-large"
  hidden_size: 1024
  num_heads: 8
  dropout: 0.1
  use_lora: false

data:
  train_path: "data/processed/train.jsonl"
  val_path:   "data/processed/val.jsonl"
  test_path:  "data/processed/test.jsonl"
  max_persona_len:   128
  max_context_len:   512
  max_response_len:  256
  max_history_turns: 5
  num_workers: 4            # DataLoader worker processes per GPU

training:
  epochs: 10
  per_gpu_batch_size: 32    # 4 GPUs × 32 = 128 effective batch per step
  gradient_accumulation_steps: 1   # effective_batch = per_gpu × n_gpu × accum
  lr: 2e-5
  warmup_steps: 200
  weight_decay: 0.01
  gradient_clip: 1.0
  eval_steps: 200           # global steps between validation runs
  mixed_precision: "bf16"   # RTX 5090 has native BF16; use "fp16" for older GPUs
  seed: 42

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

evaluation:
  binary_threshold: 0.5
  fine_threshold:   0.4

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

output:
  checkpoint_dir: "checkpoints/detector"