{ "dataset": { "repo_id": "open-cloth/full-second-bonus-fold", "root": "data/open-cloth/full-second-bonus-fold", "episodes": null, "image_transforms": { "enable": true, "max_num_transforms": 3, "random_order": false, "tfs": { "color_jitter": { "weight": 6.0, "type": "ColorJitter", "kwargs": { "brightness": [ 0.7, 1.3 ], "contrast": [ 0.7, 1.3 ], "saturation": [ 0.7, 1.3 ], "hue": [ -0.1, 0.1 ] } }, "blur": { "weight": 1.5, "type": "GaussianBlur", "kwargs": { "kernel_size": 3, "sigma": [ 0.1, 0.8 ] } }, "identity": { "weight": 4.0, "type": "Identity", "kwargs": {} }, "grayscale": { "weight": 1.5, "type": "RandomGrayscale", "kwargs": { "p": 1.0 } }, "sharpness": { "weight": 2.0, "type": "SharpnessJitter", "kwargs": { "sharpness": [ 0.5, 1.5 ] } }, "noise": { "weight": 1.0, "type": "GaussianNoise", "kwargs": { "mean": 0.0, "sigma": 0.02 } } } }, "revision": null, "use_imagenet_stats": true, "video_backend": "pyav", "return_uint8": false, "streaming": false }, "env": null, "policy": { "type": "diffusion", "n_obs_steps": 4, "input_features": { "observation.state": { "type": "STATE", "shape": [ 6 ] }, "observation.images.gripper": { "type": "VISUAL", "shape": [ 3, 480, 640 ] } }, "output_features": { "action": { "type": "ACTION", "shape": [ 6 ] } }, "device": "cuda", "use_amp": true, "use_peft": false, "push_to_hub": true, "repo_id": "open-cloth/diffusion-full-second-bonus-fold-aug", "private": null, "tags": null, "license": null, "pretrained_path": "outputs/train/full-second-bonus-fold-aug/checkpoints/last/pretrained_model", "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": [ 320, 480 ], "crop_ratio": 0.9, "crop_shape": [ 288, 432 ], "crop_is_random": true, "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1", "use_group_norm": false, "spatial_softmax_num_keypoints": 64, "use_separate_rgb_encoder_per_camera": true, "down_dims": [ 256, 512, 1024 ], "kernel_size": 5, "n_groups": 8, "diffusion_step_embed_dim": 128, "use_film_scale_modulation": true, "noise_scheduler_type": "DDIM", "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": 10, "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": "outputs/train/full-second-bonus-fold-aug", "job_name": "full-second-bonus-fold-aug", "resume": true, "seed": 1000, "cudnn_deterministic": false, "num_workers": 24, "batch_size": 64, "prefetch_factor": 4, "persistent_workers": true, "steps": 100000, "eval_freq": 20000, "log_freq": 3, "tolerance_s": 0.0001, "save_checkpoint": true, "save_freq": 5000, "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" }, "eval": { "n_episodes": 50, "batch_size": 19, "use_async_envs": true }, "wandb": { "enable": true, "disable_artifact": false, "project": "open-cloth", "entity": null, "notes": null, "run_id": "08h5fyoi", "mode": null, "add_tags": true }, "peft": null, "sample_weighting": null, "rename_map": {}, "checkpoint_path": "outputs/train/full-second-bonus-fold-aug/checkpoints/last" }