VLA/workspace/lerobot_example/config_qact_from_vlm.yml

# Train from Qwen-2.5-VL

# Model and paths configuration
log_name: "robotic_training"
log_project: "vla_training"
model_type: qwen2_5
pretrained_wallx_path: "/path/to/wallx_model/"  # Must set
save_path: "/path/to/workspace/"                # Must set
use_fast_tokenizer: True                       # True: train FAST, False: train Flow
action_tokenizer_path: "/path/to/fast/"         # Must set if use_fast_tokenizer is true
qwen_vl_act_config_path: "wall-x/workspace/lerobot_example/qwen25_config.json"


# Torch Profile
profile: False
profile_save_path: /path/to/profile/
profile_wait_iters: 10
profile_warmup_iters: 5
profile_active_iters: 2

# Training hyperparameters
num_warmup_steps: 100
num_training_steps: 64000000
learning_rate: 0.00009
min_lr: 0.00005
num_epoch: 100
gradient_accumulation_steps: 1
batch_size_per_gpu: 8
padding_side: left
epoch_save_interval: 10

# Training optimization settings
FSDP2: True
torch_compile: False

# Robot configuration - Define degrees of freedom for each component
dof_config:
  follow_left_ee_cartesian_pos: 3      # Left end-effector Cartesian position
  follow_left_ee_rotation: 3           # Left end-effector rotation
  follow_left_gripper: 1               # Left gripper control
  follow_right_ee_cartesian_pos: 3     # Right end-effector Cartesian position
  follow_right_ee_rotation: 3          # Right end-effector rotation
  follow_right_gripper: 1              # Right gripper control
  head_actions: 2                      # Head/camera movement
  height: 1                            # Mobile base height control
  car_pose: 3                          # Mobile base pose (x, y, theta)

# Agent proprioception configuration (typically matches DOF config)
agent_pos_config:
  follow_left_ee_cartesian_pos: 3
  follow_left_ee_rotation: 3
  follow_left_gripper: 1
  follow_right_ee_cartesian_pos: 3
  follow_right_ee_rotation: 3
  follow_right_gripper: 1
  head_actions: 2
  height: 1
  car_pose: 3

# # Checkpoint resuming configuration
# resume:
#   ckpt: "/path/to/resume_model/"
#   load_ckpt_only: true

norm_stats_path: "/path/to/norm_stats.json"

enable_customized_robot_config: true
customized_robot_config:
  name: "physical-intelligence/libero"
  customized_dof_config:
    "action_left_shoulder" : 1
    "action_left_elbow" : 1
    "action_left_forearm_roll" : 1
    "action_left_wrist_angle" : 1
    "action_left_wrist_rotate" : 1
    "action_left_gripper" : 1
    "action_right_waist" : 1
    "action_right_shoulder" : 1
    "action_right_elbow" : 1
    "action_right_forearm_roll" : 1
    "action_right_wrist_angle" : 1
    "action_right_wrist_rotate" : 1
    "action_right_gripper" : 1

  customized_agent_pos_config:
    "state_left_shoulder" : 1
    "state_left_elbow" : 1
    "state_left_forearm_roll" : 1
    "state_left_wrist_angle" : 1
    "state_left_wrist_rotate" : 1
    "state_left_gripper" : 1
    "state_right_waist" : 1
    "state_right_shoulder" : 1
    "state_right_elbow" : 1
    "state_right_forearm_roll" : 1
    "state_right_wrist_angle" : 1
    "state_right_wrist_rotate" : 1
    "state_right_gripper" : 1

# Data configuration
data:
  use_lerobot: true

  # LeRobot dataset configuration
  lerobot_config:
    repo_id: "lerobot/aloha_mobile_cabinet"
    root: null
    episodes: null
    image_transforms: null
    delta_timestamps: null
    tolerance_s: 1e-4
    revision: null
    force_cache_sync: false
    download_videos: true
    video_backend: null

  action_horizon: 32
  train_test_split: 0.95

  # Action keys for observation and prediction
  obs_action_keys:
    - follow_left_ee_cartesian_pos
    - follow_left_ee_rotation
    - follow_left_gripper
    - follow_right_ee_cartesian_pos
    - follow_right_ee_rotation
    - follow_right_gripper
    - head_actions
    - height
    - car_pose

  predict_action_keys:
    - follow_left_ee_cartesian_pos
    - follow_left_ee_rotation
    - follow_left_gripper
    - follow_right_ee_cartesian_pos
    - follow_right_ee_rotation
    - follow_right_gripper
    - head_actions
    - height
    - car_pose

  # Image resolution configuration for different camera views
  resolution:
    face_view: 256
    left_wrist_view: 256
    right_wrist_view: 256
    move1_view: 256
    move2_view: 256
    top_view: 256
    wall_view: 256
    multi_modal: 256