{ "dataset": { "repo_id": "local_dataset", "repo_type": "dataset", "root": "/root/.cache/huggingface/hub/datasets--UBTECH-Robotics--challenge2026_dataset/snapshots/33df931d1f27951a39a3a4d1280080620f932ae6/Packing_Box", "episodes": null, "exclude_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": "torchcodec", "return_uint8": false, "depth_output_unit": "mm", "streaming": false, "eval_split": 0.05 }, "env": null, "policy": { "type": "diffusion", "n_obs_steps": 2, "input_features": { "observation.state": { "type": "STATE", "shape": [ 20 ] }, "observation.images.head_left": { "type": "VISUAL", "shape": [ 3, 480, 640 ] }, "observation.images.head_right": { "type": "VISUAL", "shape": [ 3, 480, 640 ] }, "observation.images.wrist_left": { "type": "VISUAL", "shape": [ 3, 480, 640 ] }, "observation.images.wrist_right": { "type": "VISUAL", "shape": [ 3, 480, 640 ] } }, "output_features": { "action": { "type": "ACTION", "shape": [ 20 ] } }, "device": "cuda", "use_amp": false, "use_peft": false, "push_to_hub": false, "repo_id": null, "private": null, "tags": null, "license": null, "pretrained_path": null, "pretrained_revision": null, "horizon": 64, "n_action_steps": 32, "normalization_mapping": { "VISUAL": "MEAN_STD", "STATE": "MIN_MAX", "ACTION": "MIN_MAX" }, "drop_n_last_frames": 7, "vision_backbone": "resnet18", "resize_shape": null, "crop_ratio": 1.0, "crop_shape": null, "crop_is_random": true, "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1", "use_group_norm": false, "spatial_softmax_num_keypoints": 32, "use_separate_rgb_encoder_per_camera": true, "down_dims": [ 512, 1024, 2048 ], "kernel_size": 5, "n_groups": 8, "diffusion_step_embed_dim": 128, "use_film_scale_modulation": true, "gradient_checkpointing": false, "noise_scheduler_type": "DDPM", "num_train_timesteps": 100, "beta_schedule": "squaredcos_cap_v2", "beta_start": 0.0001, "beta_end": 0.02, "prediction_type": "epsilon", "clip_sample": true, "clip_sample_range": 1.0, "num_inference_steps": null, "compile_model": false, "compile_mode": "reduce-overhead", "do_mask_loss_for_padding": false, "optimizer_lr": 0.0001, "optimizer_betas": [ 0.95, 0.999 ], "optimizer_eps": 1e-08, "optimizer_weight_decay": 1e-06, "scheduler_name": "cosine", "scheduler_warmup_steps": 500 }, "reward_model": null, "output_dir": "/kaggle/working/diffusion_policy_task4", "job_name": "diffusion", "resume": false, "seed": 1000, "cudnn_deterministic": false, "num_workers": 2, "batch_size": 4, "prefetch_factor": 4, "persistent_workers": true, "dataloader_multiprocessing_context": "spawn", "steps": 15000, "env_eval_freq": 20000, "log_freq": 50, "eval_steps": 0, "max_eval_samples": 0, "tolerance_s": 0.0001, "save_checkpoint": true, "save_freq": 15000, "checkpoint_format": "safetensors", "use_policy_training_preset": true, "optimizer": { "type": "adam", "lr": 0.0001, "weight_decay": 1e-06, "grad_clip_norm": 10.0, "betas": [ 0.95, 0.999 ], "eps": 1e-08 }, "scheduler": { "type": "diffuser", "num_warmup_steps": 500, "name": "cosine" }, "parallelism": { "dp_replicate": 1, "dp_shard": 1, "context_parallel": { "ring_degree": 1, "ulysses_degree": 1 }, "cfg_parallel": 1 }, "accelerator": { "mixed_precision": "no", "gradient_accumulation": { "steps": 1 }, "fsdp": { "reshard_after_forward": true, "wrap_modules": null, "min_num_params": null, "cpu_offload": false, "ignored_modules": null }, "ddp": { "find_unused_parameters": true, "gradient_as_bucket_view": false, "static_graph": false }, "compile": { "enabled": false, "backend": "inductor", "mode": null, "regional": true }, "activation_checkpointing": { "mode": "none" } }, "eval": { "n_episodes": 50, "batch_size": 2, "use_async_envs": true, "recording": false, "recording_repo_id": null, "recording_private": false }, "ema": { "enable": false, "decay": null, "update_after_step": 0, "inv_gamma": 1.0, "power": 0.75, "min_decay": 0.0, "max_decay": 0.9999, "use_for_eval": true }, "wandb": { "enable": false, "disable_artifact": false, "project": "lerobot", "entity": null, "notes": null, "run_id": null, "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 }