run:
  seed: 42
  deterministic: true
  experiment_name: clip_dino_gnn_bipartite
  output_dir: outputs
  save_every_n_epochs: 1
  smoke_profile:
    epochs: 2
    batch_size: 8
    eval_batch_size: 8

training:
  stage1:
    enabled: true
    epochs: 8
    freeze_encoders: true
    lr_head: 0.001
    lr_encoder: 0.0
  stage2:
    enabled: true
    epochs: 20
    freeze_encoders: false
    unfreeze_top_n_layers: 2
    lr_head: 0.0005
    lr_encoder: 0.00001

optimization:
  optimizer: adamw
  weight_decay: 0.0001
  betas:
    - 0.9
    - 0.999
  grad_clip_norm: 1.0
  gradient_accumulation_steps: 1
  mixed_precision: true

scheduler:
  type: cosine_with_warmup
  warmup_ratio: 0.1
  min_lr: 0.0000001

batching:
  batch_size: 8
  eval_batch_size: 8

loss:
  bce:
    enabled: true
    pos_weight_mode: inverse_frequency
  contrastive:
    enabled: true
    type: infonce
    temperature: 0.07
    lambda: 0.1
    positive_sampling: same_adjective_group
    negative_sampling: conflicting_groups

early_stopping:
  enabled: true
  monitor: val_map
  mode: max
  patience: 8

checkpoint:
  enabled: true
  monitor: val_map
  mode: max
  save_best_only: true