{ "action": { "dimension": 14, "execute_horizon": 16, "horizon": 32, "padding": "end_of_episode_clamp_to_last_frame_supervised", "representation": "14-D absolute joint/qpos" }, "benchmark": "robotwin2", "data": { "camera_order": [ "head", "left_wrist", "right_wrist" ], "codec": { "decode_clip": false, "encode_clamp_sigma": 12.0, "grippers": "2x-1", "joints": "zscore_mean_std_all_clean_frames", "statistics": "codec_statistics.json", "version": "reswam-robotwin-absolute-qpos-zscore-joints-affine-grippers-14d-v1" }, "metadata_frequency_hz": 50, "preprocess_to_256": "direct_bicubic_antialias_no_crop", "vlm_camera_order": [ "head", "left_wrist", "right_wrist" ] }, "dataset": { "action_dimension": 14, "action_representation": "14-D absolute joint/qpos", "camera_order": [ "head", "left_wrist", "right_wrist" ], "cleaned_episodes": 26617, "cleaning_order": [ "static_cleaner", "outlier_episode_deletion" ], "frames": 4933470, "hf_repo": "yuanty/robotwin2.0-fastwam", "outlier_limit": "closed [-pi,pi] excluding dimensions 6 and 13", "sampler": "uniform_concat_every_clean_frame_end_clamped_supervised", "source_episodes": 27500, "state_dimension": 14, "state_representation": "14-D current qpos", "static_margin": 1, "static_threshold": 1e-06, "tasks": 50 }, "evaluation": { "base_seed": 0, "bspline_smoothing": { "degree": 3, "enabled": true, "num_ctrl_pts": 8 }, "conditions": [ "clean", "randomized" ], "execute_horizon": 16, "instruction_type": "unseen", "prediction_horizon": 32, "tasks": 50, "total_episodes": 10000, "trials_per_task": 100 }, "flow": { "action_noise": "independent_gaussian", "action_scheduler_shift": 1, "action_tau": "independent_uniform_shifted", "inference_rounds": 10, "synchronous_commit": true, "world_noise": "independent_gaussian", "world_scheduler_shift": 5, "world_tau": "independent_uniform_shifted" }, "model": { "dino": { "architecture": "DINOv3-B/16", "combine": "arithmetic_mean", "frozen": true, "model_id": "facebook/dinov3-vitb16-pretrain-lvd1689m", "remove_prefix_tokens": true, "selected_blocks": [ 8, 10 ], "spatial_pooling": "2x2", "target_token_ln": true, "tokens": 64 }, "expert": { "depth": 12, "expert_parameter_count": 493608462, "ffn_dim": 4096, "heads": 16, "hidden_dim": 1024 }, "rynnbrain": { "backbone_parameter_count": 1755487104, "repo": "Alibaba-DAMO-Academy/RynnBrain1.1-2B", "text_hidden_size": 2048, "text_layers": 16, "vision_layers": 24 } }, "optimizer": { "betas": [ 0.9, 0.95 ], "clip_grad_norm": 1.0, "expert_min_lr": 1e-05, "expert_peak_lr": 0.0001, "name": "AdamW", "precision": "bfloat16", "vlm_min_lr": 1e-06, "vlm_peak_lr": 1e-05, "weight_decay": 1e-08 }, "schema_version": "reswam-robotwin2-config-v1", "training": { "fsdp": "FULL_SHARD", "global_batch": 256, "gradient_accumulation": 2, "microbatch": 32, "seed": 20260907, "world_size": 4 }, "world": { "camera": "head", "loss_weight": 0.1, "objective": "endpoint_only_extra_LN_delta", "target_offset": 32 } }