| { |
| "dataset": { |
| "repo_id": "local/factory_conveyor_level2_seeded", |
| "root": "/projects/haitian003ssd/Dataset/factory_conveyor_level2_seeded", |
| "episodes": null, |
| "image_transforms": { |
| "enable": false, |
| "max_num_transforms": 3, |
| "random_order": false, |
| "tfs": { |
| "brightness": { |
| "weight": 1.0, |
| "type": "ColorJitter", |
| "kwargs": { |
| "brightness": [ |
| 0.8, |
| 1.2 |
| ] |
| } |
| }, |
| "contrast": { |
| "weight": 1.0, |
| "type": "ColorJitter", |
| "kwargs": { |
| "contrast": [ |
| 0.8, |
| 1.2 |
| ] |
| } |
| }, |
| "saturation": { |
| "weight": 1.0, |
| "type": "ColorJitter", |
| "kwargs": { |
| "saturation": [ |
| 0.5, |
| 1.5 |
| ] |
| } |
| }, |
| "hue": { |
| "weight": 1.0, |
| "type": "ColorJitter", |
| "kwargs": { |
| "hue": [ |
| -0.05, |
| 0.05 |
| ] |
| } |
| }, |
| "sharpness": { |
| "weight": 1.0, |
| "type": "SharpnessJitter", |
| "kwargs": { |
| "sharpness": [ |
| 0.5, |
| 1.5 |
| ] |
| } |
| }, |
| "affine": { |
| "weight": 1.0, |
| "type": "RandomAffine", |
| "kwargs": { |
| "degrees": [ |
| -5.0, |
| 5.0 |
| ], |
| "translate": [ |
| 0.05, |
| 0.05 |
| ] |
| } |
| } |
| } |
| }, |
| "revision": null, |
| "use_imagenet_stats": true, |
| "video_backend": "pyav", |
| "return_uint8": false, |
| "depth_output_unit": "mm", |
| "streaming": false, |
| "eval_split": 0.0 |
| }, |
| "env": null, |
| "policy": { |
| "type": "fastwam", |
| "n_obs_steps": 1, |
| "input_features": { |
| "observation.images.front": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 224, |
| 224 |
| ] |
| }, |
| "observation.images.overview": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 224, |
| 224 |
| ] |
| }, |
| "observation.images.wrist": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 224, |
| 224 |
| ] |
| }, |
| "observation.state": { |
| "type": "STATE", |
| "shape": [ |
| 10 |
| ] |
| } |
| }, |
| "output_features": { |
| "action": { |
| "type": "ACTION", |
| "shape": [ |
| 10 |
| ] |
| } |
| }, |
| "device": "cuda", |
| "use_amp": false, |
| "use_peft": false, |
| "push_to_hub": false, |
| "repo_id": null, |
| "private": null, |
| "tags": null, |
| "license": null, |
| "pretrained_path": "lerobot/fastwam_base", |
| "pretrained_revision": null, |
| "action_dim": 10, |
| "proprio_dim": 10, |
| "action_horizon": 32, |
| "n_action_steps": 10, |
| "num_video_frames": 33, |
| "action_video_freq_ratio": 4, |
| "image_size": [ |
| 224, |
| 672 |
| ], |
| "context_len": 128, |
| "model_id": "Wan-AI/Wan2.2-TI2V-5B", |
| "tokenizer_model_id": "google/umt5-xxl", |
| "text_encoder_model_id": "Wan-AI/Wan2.2-TI2V-5B-Diffusers", |
| "base_model_id": "lerobot/fastwam_base", |
| "tokenizer_max_len": 128, |
| "load_text_encoder": true, |
| "mot_checkpoint_mixed_attn": false, |
| "torch_dtype": "bfloat16", |
| "prompt_template": "A video recorded from a robot's point of view executing the following instruction: {task}", |
| "num_inference_steps": 10, |
| "inference_seed": 42, |
| "rand_device": "cpu", |
| "text_cfg_scale": 1.0, |
| "negative_prompt": "", |
| "sigma_shift": null, |
| "tiled": false, |
| "fp32_attention": true, |
| "use_gradient_checkpointing": true, |
| "freeze_video_expert": false, |
| "toggle_action_dimensions": [], |
| "video_scheduler": { |
| "train_shift": 5.0, |
| "infer_shift": 5.0, |
| "num_train_timesteps": 1000 |
| }, |
| "action_scheduler": { |
| "train_shift": 5.0, |
| "infer_shift": 5.0, |
| "num_train_timesteps": 1000 |
| }, |
| "loss": { |
| "lambda_video": 1.0, |
| "lambda_action": 1.0 |
| }, |
| "video_dit_config": { |
| "patch_size": [ |
| 1, |
| 2, |
| 2 |
| ], |
| "in_dim": 48, |
| "hidden_dim": 3072, |
| "ffn_dim": 14336, |
| "freq_dim": 256, |
| "text_dim": 4096, |
| "out_dim": 48, |
| "num_heads": 24, |
| "attn_head_dim": 128, |
| "num_layers": 30, |
| "eps": 1e-06, |
| "seperated_timestep": true, |
| "use_gradient_checkpointing": true, |
| "video_attention_mask_mode": "first_frame_causal", |
| "action_conditioned": false, |
| "action_dim": 10, |
| "action_group_causal_mask_mode": "group_diagonal", |
| "fp32_attention": true |
| }, |
| "action_dit_config": { |
| "action_dim": 10, |
| "hidden_dim": 1024, |
| "ffn_dim": 4096, |
| "num_heads": 24, |
| "attn_head_dim": 128, |
| "num_layers": 30, |
| "text_dim": 4096, |
| "freq_dim": 256, |
| "eps": 1e-06, |
| "use_gradient_checkpointing": true, |
| "fp32_attention": true |
| }, |
| "normalization_mapping": { |
| "VISUAL": "IDENTITY", |
| "STATE": "MEAN_STD", |
| "ACTION": "MEAN_STD" |
| }, |
| "optimizer_lr": 0.0001, |
| "optimizer_weight_decay": 0.01 |
| }, |
| "reward_model": null, |
| "output_dir": "/projects/haitian003ssd/ICRA2027-baseline/fast-wam/train_outputs/fastwam_factory_conveyor_level2_110767", |
| "job_name": "fastwam_factory_conveyor_level2", |
| "resume": false, |
| "seed": 1000, |
| "cudnn_deterministic": false, |
| "num_workers": 0, |
| "batch_size": 8, |
| "prefetch_factor": 4, |
| "persistent_workers": true, |
| "steps": 80000, |
| "env_eval_freq": 20000, |
| "log_freq": 50, |
| "eval_steps": 0, |
| "max_eval_samples": 0, |
| "tolerance_s": 0.0001, |
| "save_checkpoint": true, |
| "save_freq": 40000, |
| "use_policy_training_preset": true, |
| "optimizer": { |
| "type": "adamw", |
| "lr": 0.0001, |
| "weight_decay": 0.01, |
| "grad_clip_norm": 10.0, |
| "betas": [ |
| 0.9, |
| 0.999 |
| ], |
| "eps": 1e-08 |
| }, |
| "scheduler": null, |
| "eval": { |
| "n_episodes": 50, |
| "batch_size": 50, |
| "use_async_envs": true, |
| "recording": false, |
| "recording_repo_id": null, |
| "recording_private": false |
| }, |
| "wandb": { |
| "enable": true, |
| "disable_artifact": false, |
| "project": "fastwam", |
| "entity": null, |
| "notes": null, |
| "run_id": "c27a20qd", |
| "mode": null, |
| "add_tags": true |
| }, |
| "peft": null, |
| "job": { |
| "target": null, |
| "image": "huggingface/lerobot-gpu:latest", |
| "timeout": "2d", |
| "detach": false, |
| "tags": [] |
| }, |
| "save_checkpoint_to_hub": false, |
| "sample_weighting": null, |
| "rename_map": {}, |
| "checkpoint_path": null |
| } |
