run_id: robodojo_v21_all_h50_q99_qwenoft
run_root_dir: ./playground/Checkpoints
seed: 42
wandb_entity: your_wandb_entity
wandb_project: llavavla
is_debug: false
version_id: '0.21'
framework:
  name: QwenOFT
  qwenvl:
    base_vlm: Qwen/Qwen3-VL-4B-Instruct
    attn_implementation: flash_attention_2
    vl_hidden_dim: 2048
  action_model:
    action_model_type: MLP
    action_dim: 14
    action_hidden_dim: 2560
    future_action_window_size: 49
    past_action_window_size: 0
    hidden_size: 1024
    add_pos_embed: true
    max_seq_len: 1024
    state_dim: 14
    action_horizon: 50
    repeated_diffusion_steps: 8
    noise_beta_alpha: 1.5
    noise_beta_beta: 1.0
    noise_s: 0.999
    num_timestep_buckets: 1000
    num_inference_timesteps: 4
    num_target_vision_tokens: 32
    diffusion_model_cfg:
      dropout: 0.2
      final_dropout: true
      interleave_self_attention: true
      norm_type: ada_norm
      num_layers: 16
      output_dim: 2560
      positional_embeddings: null
      cross_attention_dim: 2048
  dino:
    dino_backbone: dinov2_vits14
datasets:
  vlm_data:
    dataset_py: vlm_datasets
    dataformat: llava_json
    dataset_use: sharegpt4v_coco
    eval_dataset: sharegpt4v_coco
    data_flatten: false
    base_interval: 2
    max_pixels: 50176
    min_pixels: 784
    model_max_length: 2048
    model_type: qwen2.5vl
    per_device_batch_size: 4
  vla_data:
    dataset_py: lerobot_datasets
    include_state: true
    data_root_dir: ./playground/Datasets
    data_mix: robodojo_v21_all_h50_q99
    action_type: abs_qpos
    action_mode: abs
    per_device_batch_size: 16
    load_all_data_for_training: true
    obs_image_size:
    - 224
    - 224
    video_backend: torchvision_av
trainer:
  max_train_steps: 150000
  num_warmup_steps: 5000
  save_interval: 10000
  eval_interval: 100
  learning_rate:
    base: 1.0e-05
    qwen_vl_interface: 1.0e-05
    action_model: 0.0001
  lr_scheduler_type: cosine_with_min_lr
  scheduler_specific_kwargs:
    min_lr: 5.0e-07
  freeze_modules: ''
  loss_scale:
    vla: 1.0
    vlm: 0.0
  max_grad_norm: 1.0
  weight_decay: 0.0
  logging_frequency: 10
  gradient_clipping: 1.0
  gradient_accumulation_steps: 1
  gradient_checkpointing: true
  optimizer:
    name: AdamW
    betas:
    - 0.9
    - 0.95
    eps: 1.0e-08
    weight_decay: 1.0e-08
  is_resume: true
config_yaml: examples/simBenchmarks/RoboDojo/train_files/starvla_robodojo_v21_qwenoft_h50_q99.yaml
output_dir: ./playground/Checkpoints/robodojo_v21_all_h50_q99_qwenoft