datasets:
  vla_data:
    CoT_prompt: Your task is {instruction}. To identify the key objects for your task.
      Locate their bounding boxes in [x1,y1,x2,y2] format.
    data_mix: multi_robot
    data_root_dir: playground/Datasets/VLA_data
    dataset_py: lerobot_datasets
    image_size:
    - 224
    - 224
    per_device_batch_size: 32
    video_backend: torchvision_av
framework:
  action_model:
    action_dim: 32
    action_hidden_dim: 2560
    action_model_type: DiT-B
    future_action_window_size: 15
    past_action_window_size: 0
  name: QwenOFT_xrobot
  qwenvl:
    base_vlm: playground/Pretrained_models/Qwen3-VL-4B-Instruct-Action
output_dir: ./results/Checkpoints/0417_multi_robot_QwenOFT_xrobot
run_id: 0417_multi_robot_QwenOFT_xrobot
run_root_dir: ./results/Checkpoints
seed: 42
trainer:
  eval_interval: 100
  freeze_modules: null
  gradient_accumulation_steps: 1
  gradient_clipping: 1.0
  is_resume: false
  learning_rate:
    action_model: 0.0001
    base: 1.0e-05
    qwen_vl_interface: 1.0e-05
  logging_frequency: 100
  lr_scheduler_type: cosine_with_min_lr
  max_train_steps: 100000
  num_warmup_steps: 5000
  optimizer:
    betas:
    - 0.9
    - 0.95
    eps: 1.0e-08
    weight_decay: 1.0e-08
  save_interval: 10000
  scheduler_specific_kwargs:
    min_lr: 5.0e-07
wandb_entity: zwanggk
wandb_project: starVLA_multiRobo