Downloads · 30 days
0
multi_task_dit_towel_v1
seelanrohan/multi_task_dit_towel_v1
multi_task_dit_towel_v1 is a machine learning model from seelanrohan. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
- Model: multitaskdit - Policy type: multitaskdit - Dataset: ["['smalltowelfoldingattempt3truncated384'", "'smalltowelfoldingattempt4truncated384'", "'smalltowelfoldingattempt5truncated384']"] - Steps: 80k, batchsize=…
Access
Public
Updated Jul 15, 2026
Repo size
22.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors22.6 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 15, 2026
- Updated
- Jul 15, 2026
- SHA
- eaa55104
Model card
From the Hugging Face model README
multi_task_dit Training Run
Summary
- Model: multi_task_dit
- Policy type: multi_task_dit
- Dataset: ["['small_towel_folding_attempt_3_truncated_384'", "'small_towel_folding_attempt_4_truncated_384'", "'small_towel_folding_attempt_5_truncated_384']"]
- Steps: 80k, batch_size=200
- Optimizer: Adam lr=2e-5, diffuser schedule w/ 0 warmup steps
- Checkpoints: every 10k
- push_to_hub: false
- wandb: enabled (project=lerobot)
Full Config
{'batch_size': 200,
'checkpoint_path': None,
'cudnn_deterministic': False,
'dataset': {'episodes': None,
'image_transforms': {'enable': False,
'max_num_transforms': 3,
'random_order': False,
'tfs': {'affine': {'kwargs': {'degrees': (-5.0,
5.0),
'translate': (0.05,
0.05)},
'type': 'RandomAffine',
'weight': 1.0},
'brightness': {'kwargs': {'brightness': (0.8,
1.2)},
'type': 'ColorJitter',
'weight': 1.0},
'contrast': {'kwargs': {'contrast': (0.8,
1.2)},
'type': 'ColorJitter',
'weight': 1.0},
'hue': {'kwargs': {'hue': (-0.05,
0.05)},
'type': 'ColorJitter',
'weight': 1.0},
'saturation': {'kwargs': {'saturation': (0.5,
1.5)},
'type': 'ColorJitter',
'weight': 1.0},
'sharpness': {'kwargs': {'sharpness': (0.5,
1.5)},
'type': 'SharpnessJitter',
'weight': 1.0}}},
'repo_id': ["['small_towel_folding_attempt_3_truncated_384'",
"'small_towel_folding_attempt_4_truncated_384'",
"'small_towel_folding_attempt_5_truncated_384']"],
'return_uint8': False,
'revision': None,
'root': '/workspace/datasets/smallTowelFolding',
'streaming': False,
'use_imagenet_stats': True,
'video_backend': 'pyav'},
'env': None,
'eval': {'batch_size': 50, 'n_episodes': 50, 'use_async_envs': True},
'eval_freq': 0,
'job_name': 'multi_task_dit_towel_batch200_80k_h264_v3',
'log_freq': 200,
'num_workers': 8,
'optimizer': {'betas': (0.95, 0.999),
'eps': 1e-08,
'grad_clip_norm': 10.0,
'lr': 2e-05,
'weight_decay': 0.0},
'output_dir': PosixPath('/workspace/outputs/multi_task_dit_towel_v1'),
'peft': None,
'persistent_workers': True,
'policy': {'beta_end': 0.02,
'beta_schedule': 'squaredcos_cap_v2',
'beta_start': 0.0001,
'clip_sample': True,
'clip_sample_range': 1.0,
'device': 'cuda',
'do_mask_loss_for_padding': False,
'drop_n_last_frames': 7,
'dropout': 0.1,
'hidden_dim': 512,
'horizon': 32,
'image_crop_is_random': True,
'image_crop_shape': (224, 224),
'image_resize_shape': (256, 256),
'input_features': {},
'integration_method': 'euler',
'license': None,
'n_action_steps': 24,
'n_obs_steps': 2,
'noise_scheduler_type': 'DDPM',
'normalization_mapping': {'ACTION': <NormalizationMode.MIN_MAX: 'MIN_MAX'>,
'STATE': <NormalizationMode.MIN_MAX: 'MIN_MAX'>,
'VISUAL': <NormalizationMode.MEAN_STD: 'MEAN_STD'>},
'num_heads': 8,
'num_inference_steps': None,
'num_integration_steps': 100,
'num_layers': 6,
'num_train_timesteps': 100,
'objective': 'diffusion',
'optimizer_betas': (0.95, 0.999),
'optimizer_eps': 1e-08,
'optimizer_lr': 2e-05,
'optimizer_weight_decay': 0.0,
'output_features': {},
'prediction_type': 'epsilon',
'pretrained_path': None,
'private': None,
'push_to_hub': False,
'repo_id': None,
'rope_base': 10000.0,
'scheduler_name': 'cosine',
'scheduler_warmup_steps': 0,
'sigma_min': 0.0,
'tags': None,
'text_encoder_name': 'openai/clip-vit-base-patch16',
'timestep_embed_dim': 256,
'timestep_sampling_alpha': 1.5,
'timestep_sampling_beta': 1.0,
'timestep_sampling_s': 0.999,
'timestep_sampling_strategy': 'beta',
'tokenizer_max_length': 77,
'tokenizer_padding': 'max_length',
'tokenizer_padding_side': 'right',
'tokenizer_truncation': True,
'use_amp': False,
'use_peft': False,
'use_positional_encoding': False,
'use_rope': True,
'use_separate_rgb_encoder_per_camera': False,
'vision_encoder_lr_multiplier': 0.1,
'vision_encoder_name': 'openai/clip-vit-base-patch16'},
'prefetch_factor': 2,
'rename_map': {},
'resume': False,
'reward_model': None,
'sample_weighting': None,
'save_checkpoint': True,
'save_freq': 10000,
'scheduler': {'name': 'cosine', 'num_warmup_steps': 0},
'seed': 1000,
'steps': 80000,
'tolerance_s': 0.0001,
'use_policy_training_preset': True,
'wandb': {'add_tags': True,
'disable_artifact': False,
'enable': True,
'entity': None,
'mode': None,
'notes': None,
'project': 'lerobot',
'run_id': None}}
- Created
- Jul 15, 2026
- Updated
- Jul 15, 2026