# Small-scale debug config for testing two-stage training
DATA:
  MAX_SAMPLE_INTERVAL: 200
  MEAN:
  - 0.485
  - 0.456
  - 0.406
  SEARCH:
    CENTER_JITTER: 3.5
    FACTOR: 4.0
    SCALE_JITTER: 0.5
    SIZE: 256
    NUMBER: 4
  STD:
  - 0.229
  - 0.224
  - 0.225
  TEMPLATE:
    CENTER_JITTER: 0
    FACTOR: 2.0
    SCALE_JITTER: 0
    SIZE: 128
    NUMBER: 3
  TRAIN:
    DATASETS_NAME:
    - LASOT
    DATASETS_RATIO:
    - 1
    SAMPLE_PER_EPOCH: 20        # small for debug
MODEL:
  PRETRAIN_FILE: "fast_itpn_base_clipl_e1600.pt"
  PRETRAINED_PATH: "checkpoint/ATCTrack_b.pth.tar"
  TARGET_STATE:
    ENABLE: true
    MODEL_PATH: "../Qwen/Qwen3.5-2B"
    TOKEN: "<TARGET_STATE>"
    FREEZE_QWEN: true
    TRAIN_TOKEN_EMBEDDING: true
    USE_LORA: true
    LORA_R: 8
    LORA_ALPHA: 16
    LORA_DROPOUT: 0.05
    LORA_TARGET_MODULES:
      - in_proj_qkv
      - out_proj
      - in_proj_z
      - in_proj_b
      - in_proj_a
      - q_proj
      - k_proj
      - v_proj
      - o_proj
      - gate_proj
      - up_proj
      - down_proj
    TEACHER_ENABLE: true
    TEACHER_MODEL: qwen3.5
    TEACHER_BASE_URL: http://127.0.0.1:8001/v1
    TEACHER_API_KEY: sk-no-key-required
  BACKBONE:
    TYPE: itpn_base
    STRIDE: 16
  HEAD:
    TYPE: CENTER
    NUM_CHANNELS: 256
  HIDDEN_DIM: 512
TRAIN:
  BACKBONE_MULTIPLIER: 0.1
  DROP_PATH_RATE: 0.1
  BATCH_SIZE: 1                  # bs=1 for debug
  EPOCH: 3
  GIOU_WEIGHT: 2.0
  L1_WEIGHT: 5.0
  QWEN_FORMAT_WEIGHT: 0.02
  QWEN_TEACHER_WEIGHT: 0.5
  GRAD_CLIP_NORM: 0.1
  LR: 0.0002
  QWEN_LR_MULTIPLIER: 2.0
  WARMUP_EPOCHS: 0               # skip warmup for 2-epoch debug runs
  NUM_WORKER: 0                  # 0 workers for deterministic debug
  OPTIMIZER: ADAMW
  PRINT_INTERVAL: 1
  SCHEDULER:
    TYPE: cosine
  WEIGHT_DECAY: 0.0001
  AMP: False
  FIX_BN: true
  TYPE: target_state

TEST:
  EPOCH: 240
  SEARCH_FACTOR: 4.0
  SEARCH_SIZE: 256
  TEMPLATE_FACTOR: 2.0
  TEMPLATE_SIZE: 128
  WINDOW: true
  NUM_TEMPLATES: 2