base_model: Qwen/Qwen3-Embedding-0.6B
max_length: 512

lora:
  r: 16
  alpha: 32
  dropout: 0.05
  target_modules: [q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj]

head:
  scale_init: 20.0

loss:
  label_smoothing: 0.05

optimizer:
  lora_lr: 3.0e-4
  lora_wd: 0.01
  head_lr: 2.0e-3
  head_wd: 0.0
  warmup_frac: 0.10
  final_lr_frac: 0.05

train:
  batch_size: 16
  epochs: 12
  patience: 3
  dtype: bf16          # spec; if metrics look odd on this stack, try fp32

data:
  dir: data
  taxonomy: topic_taxonomy.json
  train: train.jsonl
  validation: validation.jsonl
  test: test.jsonl
  # hard topic pairs get x2 sampling weight (mirrors the spec's "hard-pair topics x2")
  hard_pairs:
    - [soccer, sports_general]
    - [swim_club, sports_general]
    - [art_club, crafts_club]
    - [music_band, choir]
    - [flu_report, allergies]
    - [bake_sale, fundraiser]

out_root: runs