train_config.yaml

input_format:
  pred_sentinel: '[PRED]'
  template: '[REF] {reference_report}


    [PRED] {candidate_report}'
loss:
  anat: 0.5
  cand: 0.5
  cat: 1.0
  concept: 0.3
  ref: 0.5
  sev: 0.5
metrics:
  primary_metric: val_mae_K
model:
  architecture: cada_d
  attn_implementation: flash_attention_2
  backbone_name: Qwen/Qwen3-Embedding-0.6B
  chest2vec_adapter_path: /opt/project/chest2vec/export_chest2vec_0.6b_chest/contrastive
  decoder_dropout: 0.1
  decoder_ff: 2048
  decoder_heads: 8
  decoder_layers: 4
  freeze_backbone_initially: false
  lora_alpha: 64
  lora_dropout: 0.05
  lora_rank: 32
  max_decode_steps: 24
  max_length: 1280
  n_anat: 9
  n_cat: 5
  n_severity: 2
  use_lora: true
paths:
  concept_vocab_path: /opt/project/chest2vec/chest2vec_error/artifacts_v5/concept2id.json
  data_csv: /opt/project/chest2vec/create_labels/unified_variants_v5_merged.csv
  output_dir: /opt/project/chest2vec/chest2vec_error/artifacts/cada_d_6gpu
seed: 42
training:
  batch_size: 8
  bf16: true
  epochs: 20
  grad_accum_steps: 1
  gradient_checkpointing: false
  lr_backbone: 0.0001
  lr_heads: 0.0003
  max_grad_norm: 1.0
  num_workers: 4
  warmup_ratio: 0.03
  weight_decay: 0.01