{ "dataset": { "repo_id": "l5vel-peng/multitask-eefrel-h32", "repo_type": "dataset", "root": "/home/data/pej3435/.cache/l5vel_eef_merge/outputs/multitask-eefrel-h32", "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": "mtdit_spatial", "n_obs_steps": 2, "input_features": { "observation.state": { "type": "STATE", "shape": [ 13 ] }, "observation.images.left": { "type": "VISUAL", "shape": [ 3, 480, 640 ] }, "observation.images.right": { "type": "VISUAL", "shape": [ 3, 480, 640 ] }, "observation.images.wrist": { "type": "VISUAL", "shape": [ 3, 480, 640 ] }, "observation.base_pose": { "type": "STATE", "shape": [ 3 ] }, "observation.eef_state": { "type": "STATE", "shape": [ 13 ] } }, "output_features": { "action": { "type": "ACTION", "shape": [ 13 ] }, "action.eef": { "type": "ACTION", "shape": [ 13 ] } }, "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": 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": 4, "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": [ 240, 320 ], "image_crop_shape": [ 224, 224 ], "image_crop_is_random": true, "vision_feature_mode": "cls", "num_spatial_keypoints": 32, "spatial_softmax_keep_cls": true, "spatial_softmax_learnable_temperature": true, "cross_attention_heads": null, "action_stride": 1, "state_dropout_prob": 0.0, "action_loss_weighting": "none", "loss_weight_max": 4.0, "loss_gripper_dim": 9, "state_conditioning": "full", "state_feature_names": null, "masked_state_names": null, "use_relative_actions": true, "relative_exclude_joints": [ "gripper" ], "action_feature_names": [ "eef_x", "eef_y", "eef_z", "eef_xx", "eef_xy", "eef_xz", "eef_yx", "eef_yy", "eef_yz", "gripper", "base_x", "base_y", "base_yaw" ], "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": "QUANTILES" }, "optimizer_lr": 0.0003, "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/data/pej3435/Code/dev/lerobot_policy_mtdit_spatial/outputs/relrep100k/mtdit_eef", "job_name": "relrep100k_mtdit_eef", "resume": false, "seed": 1000, "cudnn_deterministic": false, "num_workers": 12, "batch_size": 64, "prefetch_factor": 4, "persistent_workers": true, "dataloader_multiprocessing_context": "spawn", "steps": 100000, "env_eval_freq": 0, "log_freq": 200, "eval_steps": 5000, "max_eval_samples": 0, "tolerance_s": 0.0001, "save_checkpoint": true, "save_freq": 10000, "checkpoint_format": "safetensors", "use_policy_training_preset": true, "optimizer": { "type": "adam", "lr": 0.0003, "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" }, "parallelism": { "dp_replicate": 1, "dp_shard": 1, "context_parallel": { "ring_degree": 1, "ulysses_degree": 1 }, "cfg_parallel": 1 }, "accelerator": { "mixed_precision": "bf16", "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": 50, "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": true, "disable_artifact": true, "project": "relative-representation-100k", "entity": null, "notes": null, "run_id": "1iqc885k", "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 }