model:
  base_model: Qwen/Qwen3-0.6B
  max_length: 512
  pooling: last_token
  dropout: 0.05
  freeze_backbone: true
  dtype: auto

training:
  seed: 42
  epochs: 5
  batch_size: 8
  gradient_accumulation_steps: 1
  learning_rate: 0.001
  weight_decay: 0.01
  max_grad_norm: 1.0
  soft_target_temperature: 0.15
  log_every: 10