{ "dataset": { "repo_id": "chomeed/robocasa365_pretrain_drydishes", "root": null, "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": 0.0 }, "env": { "type": "robocasa", "task": "DryDishes", "fps": 20, "features": { "action": { "type": "ACTION", "shape": [ 12 ] }, "pixels/robot0_agentview_left": { "type": "VISUAL", "shape": [ 256, 256, 3 ] }, "pixels/robot0_eye_in_hand": { "type": "VISUAL", "shape": [ 256, 256, 3 ] }, "pixels/robot0_agentview_right": { "type": "VISUAL", "shape": [ 256, 256, 3 ] }, "agent_pos": { "type": "STATE", "shape": [ 16 ] } }, "features_map": { "action": "action", "agent_pos": "observation.state", "pixels/robot0_agentview_left": "observation.images.robot0_agentview_left", "pixels/robot0_eye_in_hand": "observation.images.robot0_eye_in_hand", "pixels/robot0_agentview_right": "observation.images.robot0_agentview_right" }, "max_parallel_tasks": 1, "disable_env_checker": true, "episode_length": 1000, "obs_type": "pixels_agent_pos", "render_mode": "rgb_array", "camera_name": "robot0_agentview_left,robot0_eye_in_hand,robot0_agentview_right", "observation_height": 256, "observation_width": 256, "visualization_height": 512, "visualization_width": 512, "split": null, "obj_registries": [ "objaverse", "lightwheel" ] }, "policy": { "type": "multi_task_dit", "n_obs_steps": 2, "input_features": { "observation.images.robot0_eye_in_hand": { "type": "VISUAL", "shape": [ 3, 256, 256 ] }, "observation.images.robot0_agentview_left": { "type": "VISUAL", "shape": [ 3, 256, 256 ] }, "observation.images.robot0_agentview_right": { "type": "VISUAL", "shape": [ 3, 256, 256 ] }, "observation.state": { "type": "STATE", "shape": [ 16 ] } }, "output_features": { "action": { "type": "ACTION", "shape": [ 12 ] } }, "device": "cuda", "use_amp": false, "use_peft": false, "push_to_hub": true, "repo_id": "chomeed/multitask-dit-dry-dishes", "private": null, "tags": null, "license": null, "pretrained_path": null, "pretrained_revision": null, "horizon": 32, "n_action_steps": 24, "objective": "diffusion", "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, "sigma_min": 0.0, "num_integration_steps": 100, "integration_method": "euler", "timestep_sampling_strategy": "beta", "timestep_sampling_s": 0.999, "timestep_sampling_alpha": 1.5, "timestep_sampling_beta": 1.0, "hidden_dim": 512, "num_layers": 6, "num_heads": 8, "dropout": 0.1, "use_positional_encoding": false, "timestep_embed_dim": 256, "use_rope": true, "rope_base": 10000.0, "vision_encoder_name": "openai/clip-vit-base-patch16", "use_separate_rgb_encoder_per_camera": false, "vision_encoder_lr_multiplier": 0.1, "image_resize_shape": null, "image_crop_shape": [ 224, 224 ], "image_crop_is_random": true, "text_encoder_name": "openai/clip-vit-base-patch16", "tokenizer_max_length": 77, "tokenizer_padding": "max_length", "tokenizer_padding_side": "right", "tokenizer_truncation": true, "normalization_mapping": { "VISUAL": "MEAN_STD", "STATE": "MIN_MAX", "ACTION": "MIN_MAX" }, "optimizer_lr": 2e-05, "optimizer_betas": [ 0.95, 0.999 ], "optimizer_eps": 1e-08, "optimizer_weight_decay": 0.0, "scheduler_name": "cosine", "scheduler_warmup_steps": 0, "do_mask_loss_for_padding": false, "drop_n_last_frames": 7 }, "reward_model": null, "output_dir": "/home/chomeed/workspace/hdr_robot/train_ckpts/policy_learning/multi_task_dit/dry_dishes_smoke", "job_name": "robocasa_multi_task_dit", "resume": false, "seed": 1000, "cudnn_deterministic": false, "num_workers": 4, "batch_size": 32, "prefetch_factor": 4, "persistent_workers": true, "dataloader_multiprocessing_context": "spawn", "steps": 100, "env_eval_freq": 50, "log_freq": 10, "eval_steps": 0, "max_eval_samples": 0, "tolerance_s": 0.0001, "save_checkpoint": true, "save_freq": 100, "use_policy_training_preset": true, "optimizer": { "type": "adam", "lr": 2e-05, "weight_decay": 0.0, "grad_clip_norm": 10.0, "betas": [ 0.95, 0.999 ], "eps": 1e-08 }, "scheduler": { "type": "diffuser", "num_warmup_steps": 0, "name": "cosine" }, "eval": { "n_episodes": 1, "batch_size": 1, "use_async_envs": false, "recording": false, "recording_repo_id": null, "recording_private": false }, "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 }