Add Qwen Bridge 29K common-start config.full.yaml

qwen_bridge_common_start_29k/config.full.yaml

@@ -0,0 +1,122 @@
+run_id: qwen3vl-groot-bridge-commonstart-scratch-15k-seed42
+run_root_dir: /data/yanfei/qwen_bridge_commonstart_20k_to30k_20260911/runs
+seed: 42
+wandb_entity: null
+wandb_project: QwenBridge-CommonStart
+is_debug: false
+version_id: '0.21'
+framework:
+  name: QwenGR00T
+  qwenvl:
+    base_vlm: /home/yanfei/miaochengyu/robotwin-infoflow/legacy_bridge_runtime/compat/mnt/miaochengyu/starvla-infoflow-runtime/playground/Pretrained_models/Qwen3-VL-4B-Instruct
+    attn_implementation: flash_attention_2
+    vl_hidden_dim: 2048
+    enable_gradient_checkpointing: true
+  action_model:
+    action_model_type: DiT-B
+    action_hidden_dim: 2048
+    hidden_size: 1024
+    add_pos_embed: true
+    max_seq_len: 1024
+    action_dim: 7
+    state_dim: 7
+    action_horizon: 16
+    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:
+      cross_attention_dim: 2560
+      dropout: 0.2
+      final_dropout: true
+      interleave_self_attention: true
+      norm_type: ada_norm
+      num_layers: 16
+      output_dim: 1024
+      positional_embeddings: null
+    future_action_window_size: 15
+    past_action_window_size: 0
+datasets:
+  vla_data:
+    dataset_py: lerobot_datasets
+    data_root_dir: /data/yanfei/qwen_bridge_assets/OXE_LEROBOT_DATASET
+    data_mix: bridge_rt_infoflow
+    action_type: delta_ee
+    action_mode: abs
+    precomputed_statistics_path: /home/yanfei/miaochengyu/robotwin-infoflow/legacy_bridge_runtime/compat/mnt/miaochengyu/starvla-infoflow-runtime/playground/Pretrained_models/Florence-GR00T-Bridge-RT-1/dataset_statistics.json
+    precomputed_statistics_key_map:
+      bridge_orig_lerobot: oxe_bridge
+      fractal20220817_data_lerobot: oxe_rt1
+    CoT_prompt: Your task is {instruction}. To identify the key objects for your task.
+      Locate their bounding boxes in [x1,y1,x2,y2] format.
+    per_device_batch_size: 2
+    load_all_data_for_training: true
+    obs:
+    - image_0
+    obs_image_size:
+    - 224
+    - 224
+    video_backend: torchvision_av
+    num_workers: 1
+    balance_dataset_weights: false
+    balance_trajectory_weights: false
+    traceable_sampling: true
+    expected_world_size: 1
+    dataset_provenance_path: /home/yanfei/miaochengyu/robotwin-infoflow/legacy_bridge_runtime/compat/home/miaochengyu/starVLA-infoflow-codex/protocols/bridgert/data_provenance.json
+    dataset_content_fingerprint_path: /home/yanfei/miaochengyu/robotwin-infoflow/legacy_bridge_runtime/compat/mnt/miaochengyu/starvla-infoflow-runtime/manifests/bridgert/content_fingerprints.json
+    valid_anchor_manifest_path: /home/yanfei/miaochengyu/robotwin-infoflow/legacy_bridge_runtime/compat/mnt/miaochengyu/starvla-infoflow-runtime/manifests/bridgert/valid_anchor_manifest_florence_scratch_v1.json
+    valid_anchor_manifest_migration_path: /home/yanfei/miaochengyu/robotwin-infoflow/legacy_bridge_runtime/compat/home/miaochengyu/starVLA-infoflow-codex/protocols/bridgert/valid_anchor_manifest_rng_migration_20260729.json
+    temporal_proposal_path: null
+trainer:
+  use_deepspeed: false
+  model_dtype: bfloat16
+  max_train_steps: 100000
+  stop_after_steps: 15000
+  initial_completed_steps: 0
+  num_warmup_steps: 10000
+  repeated_diffusion_steps: 4
+  evaluation_snapshot_interval: null
+  save_interval: null
+  save_steps:
+  - 21000
+  - 22000
+  - 23000
+  - 24000
+  - 25000
+  - 26000
+  - 27000
+  - 28000
+  - 29000
+  - 30000
+  save_final_checkpoint: false
+  eval_interval: null
+  pretrained_checkpoint: null
+  is_resume: true
+  allow_model_only_resume: false
+  learning_rate:
+    base: 3.0e-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: ''
+  trainable_modules: ''
+  frozen_modules_eval: false
+  logging_frequency: 10
+  gradient_clipping: 1.0
+  gradient_accumulation_steps: 24
+  save_format: pt
+  optimizer:
+    name: AdamW8bit
+    betas:
+    - 0.9
+    - 0.95
+    eps: 1.0e-08
+    weight_decay: 1.0e-08
+  operational_stop_after_steps: 30000
+config_yaml: /home/yanfei/miaochengyu/qwen_bridge_commonstart_4090_20260910/configs/qwen_bridge_commonstart_scratch_15k.yaml
+output_dir: /data/yanfei/qwen_bridge_commonstart_20k_to30k_20260911/runs/qwen3vl-groot-bridge-commonstart-scratch-15k-seed42