| framework: |
| name: QwenGR00T |
| qwenvl: |
| attn_implementation: flash_attention_2 |
| vl_hidden_dim: 2048 |
| base_vlm: ./playground/Pretrained_models/Qwen3-VL-4B-Instruct |
| dino: |
| dino_backbone: dinov2_vits14 |
| action_model: |
| action_model_type: DiT-B |
| action_hidden_dim: 2560 |
| hidden_size: 2560 |
| add_pos_embed: true |
| max_seq_len: 1024 |
| action_dim: 12 |
| state_dim: 16 |
| future_action_window_size: 15 |
| action_horizon: 16 |
| past_action_window_size: 0 |
| 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: 2560 |
| positional_embeddings: null |
| reduce_in_full_precision: true |
| datasets: |
| vlm_data: |
| dataset_py: vlm_datasets |
| dataformat: llava_json |
| dataset_use: asv2_conversation_en,asv2_detailed_description_en,asv2_region_captioning_en,coco_internvl_longcap_en,coco_karpathy_train_567_en,coco_negative_gpt4o_en,coco_poetry_zh,coco_rem_en_zh,cocorem_exist_yorn_en,cocotextv2_en,cocotextv2_gpt4o_en,okvqa_en,refcoco_grounding_aug_en,refcoco_grounding_en,tallyqa_coco_en,toloka_grounding_aug_en,vqav2_en,vsr_en |
| eval_dataset: aokvqa_cauldron_llava_format |
| data_flatten: false |
| base_interval: 2 |
| max_pixels: 50176 |
| min_pixels: 784 |
| model_max_length: 2048 |
| model_type: qwen3vl |
| per_device_batch_size: 4 |
| dataloader_module: vlm_datasets |
| vla_data: |
| dataset_py: lerobot_datasets |
| data_root_dir: /share/zhaoyiren/robocasa_dataset/v1.0 |
| data_mix: robocasa365_pretrain300 |
| action_mode: abs |
| sequential_step_sampling: false |
| CoT_prompt: Your task is {instruction}. To identify the key objects for your task. |
| Locate their bounding boxes in [x1,y1,x2,y2] format. |
| CoT_answer: bbox |
| default_image_resolution: |
| - 3 |
| - 224 |
| - 224 |
| per_device_batch_size: 16 |
| load_all_data_for_training: true |
| obs: |
| - robot0_agentview_left |
| - robot0_agentview_right |
| - robot0_eye_in_hand |
| image_size: |
| - 224 |
| - 224 |
| delete_pause_frame: false |
| video_backend: torchvision_av |
| dataset_mix: robocasa365_target_atomic |
| dataloader_module: lerobot_datasets |
| trainer: |
| enable_gradient_checkpointing: true |
| enable_mixed_precision_training: true |
| epochs: 100 |
| eval_interval: 1000000 |
| freeze_modules: '' |
| gradient_accumulation_steps: 2 |
| gradient_clipping: 1.0 |
| is_resume: false |
| learning_rate: |
| action_model: 0.0001 |
| base: 3.0e-05 |
| qwen_vl_interface: 1.0e-05 |
| logging_frequency: 10 |
| loss_scale: |
| vla: 1.0 |
| vlm: 0.1 |
| lr_scheduler_type: cosine_with_min_lr |
| max_grad_norm: 1.0 |
| max_train_steps: 120000 |
| num_warmup_steps: 5000 |
| optimizer: |
| betas: |
| - 0.9 |
| - 0.95 |
| eps: 1.0e-08 |
| name: AdamW |
| weight_decay: 1.0e-08 |
| resume_epoch: null |
| resume_step: null |
| save_interval: 10000 |
| scheduler_specific_kwargs: |
| min_lr: 1.0e-06 |
| warmup_ratio: 0.1 |
| weight_decay: 0.0 |
| environment: |
| wandb_mode: disabled |
| wandb_project: '' |
| wandb_entity: '' |
| num_gpus: 2 |
| main_process_port: 29503 |
| nccl: |
| ib_hca: mlx5_2,mlx5_3 |
| blocking_wait: 1 |
| async_error_handling: 1 |
| timeout: 10000 |
| socket_timeout_ms: 360000 |
| seed: 42 |
| run_id: qwen_gr00t_robocasa365_target_atomic |
| output_root_dir: ./results/training |
| wandb_project: VLA |
| wandb_entity: trevorzhaozhihan-zyr |
| output_dir: ./results/training/qwen_gr00t_robocasa365_target_atomic |
|
|
