Instructions to use ardalon/sequential_t1_t2_task4818_fft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use ardalon/sequential_t1_t2_task4818_fft with LeRobot:
# See https://github.com/huggingface/lerobot?tab=readme-ov-file#installation for more details git clone https://github.com/huggingface/lerobot.git cd lerobot pip install -e .[smolvla]
# Launch finetuning on your dataset python lerobot/scripts/train.py \ --policy.path=ardalon/sequential_t1_t2_task4818_fft \ --dataset.repo_id=lerobot/svla_so101_pickplace \ --batch_size=64 \ --steps=20000 \ --output_dir=outputs/train/my_smolvla \ --job_name=my_smolvla_training \ --policy.device=cuda \ --wandb.enable=true
# Run the policy using the record function python -m lerobot.record \ --robot.type=so101_follower \ --robot.port=/dev/ttyACM0 \ # <- Use your port --robot.id=my_blue_follower_arm \ # <- Use your robot id --robot.cameras="{ front: {type: opencv, index_or_path: 8, width: 640, height: 480, fps: 30}}" \ # <- Use your cameras --dataset.single_task="Grasp a lego block and put it in the bin." \ # <- Use the same task description you used in your dataset recording --dataset.repo_id=HF_USER/dataset_name \ # <- This will be the dataset name on HF Hub --dataset.episode_time_s=50 \ --dataset.num_episodes=10 \ --policy.path=ardalon/sequential_t1_t2_task4818_fft - Notebooks
- Google Colab
- Kaggle
| { | |
| "dataset": { | |
| "repo_id": "daniecraig/libero_90_no_noops_lerobot_v30", | |
| "root": null, | |
| "episodes": [ | |
| 3319, | |
| 3320, | |
| 3321, | |
| 3322, | |
| 3323, | |
| 3324, | |
| 3325, | |
| 3326, | |
| 3327, | |
| 3328, | |
| 3329, | |
| 3330, | |
| 3331, | |
| 3332, | |
| 3333, | |
| 3334, | |
| 3335, | |
| 3336, | |
| 3337, | |
| 3338, | |
| 3339, | |
| 3340, | |
| 3341, | |
| 3342, | |
| 3343, | |
| 3344, | |
| 3345, | |
| 3346, | |
| 3347, | |
| 3348, | |
| 3349, | |
| 3350, | |
| 3351, | |
| 3352, | |
| 3353, | |
| 3354, | |
| 3355, | |
| 3356, | |
| 3357, | |
| 3358, | |
| 3359, | |
| 3360, | |
| 3361, | |
| 3362, | |
| 3363, | |
| 3364, | |
| 3365 | |
| ], | |
| "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": "main", | |
| "use_imagenet_stats": true, | |
| "video_backend": "torchcodec", | |
| "streaming": false | |
| }, | |
| "env": { | |
| "type": "libero", | |
| "task": "libero_90", | |
| "fps": 30, | |
| "features": { | |
| "action": { | |
| "type": "ACTION", | |
| "shape": [ | |
| 7 | |
| ] | |
| }, | |
| "pixels/agentview_image": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 360, | |
| 360, | |
| 3 | |
| ] | |
| }, | |
| "pixels/robot0_eye_in_hand_image": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 360, | |
| 360, | |
| 3 | |
| ] | |
| }, | |
| "robot_state/eef/pos": { | |
| "type": "STATE", | |
| "shape": [ | |
| 3 | |
| ] | |
| }, | |
| "robot_state/eef/quat": { | |
| "type": "STATE", | |
| "shape": [ | |
| 4 | |
| ] | |
| }, | |
| "robot_state/eef/mat": { | |
| "type": "STATE", | |
| "shape": [ | |
| 3, | |
| 3 | |
| ] | |
| }, | |
| "robot_state/gripper/qpos": { | |
| "type": "STATE", | |
| "shape": [ | |
| 2 | |
| ] | |
| }, | |
| "robot_state/gripper/qvel": { | |
| "type": "STATE", | |
| "shape": [ | |
| 2 | |
| ] | |
| }, | |
| "robot_state/joints/pos": { | |
| "type": "STATE", | |
| "shape": [ | |
| 7 | |
| ] | |
| }, | |
| "robot_state/joints/vel": { | |
| "type": "STATE", | |
| "shape": [ | |
| 7 | |
| ] | |
| } | |
| }, | |
| "features_map": { | |
| "action": "action", | |
| "robot_state/eef/pos": "observation.state.eef_pos", | |
| "robot_state/eef/quat": "observation.state.eef_quat", | |
| "robot_state/eef/mat": "observation.state.eef_mat", | |
| "robot_state/gripper/qpos": "observation.state.gripper_qpos", | |
| "robot_state/gripper/qvel": "observation.state.gripper_qvel", | |
| "robot_state/joints/pos": "observation.state.joint_pos", | |
| "robot_state/joints/vel": "observation.state.joint_vel", | |
| "pixels/agentview_image": "observation.images.image", | |
| "pixels/robot0_eye_in_hand_image": "observation.images.image2" | |
| }, | |
| "max_parallel_tasks": 1, | |
| "disable_env_checker": true, | |
| "task_ids": [ | |
| 18 | |
| ], | |
| "episode_length": null, | |
| "obs_type": "pixels_agent_pos", | |
| "render_mode": "rgb_array", | |
| "camera_name": "agentview_image,robot0_eye_in_hand_image", | |
| "init_states": true, | |
| "camera_name_mapping": null, | |
| "observation_height": 360, | |
| "observation_width": 360, | |
| "control_mode": "relative" | |
| }, | |
| "policy": { | |
| "type": "smolvla", | |
| "n_obs_steps": 1, | |
| "input_features": { | |
| "observation.images.image": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 256, | |
| 256, | |
| 3 | |
| ] | |
| }, | |
| "observation.images.wrist_image": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 256, | |
| 256, | |
| 3 | |
| ] | |
| }, | |
| "observation.state": { | |
| "type": "STATE", | |
| "shape": [ | |
| 8 | |
| ] | |
| }, | |
| "observation.states.ee_state": { | |
| "type": "STATE", | |
| "shape": [ | |
| 6 | |
| ] | |
| }, | |
| "observation.states.joint_state": { | |
| "type": "STATE", | |
| "shape": [ | |
| 7 | |
| ] | |
| }, | |
| "observation.states.gripper_state": { | |
| "type": "STATE", | |
| "shape": [ | |
| 2 | |
| ] | |
| } | |
| }, | |
| "output_features": { | |
| "action": { | |
| "type": "ACTION", | |
| "shape": [ | |
| 7 | |
| ] | |
| } | |
| }, | |
| "device": "cuda", | |
| "use_amp": false, | |
| "use_peft": false, | |
| "push_to_hub": true, | |
| "repo_id": "ardalon/sequential_t1_t2_task4818_fft", | |
| "private": null, | |
| "tags": null, | |
| "license": null, | |
| "pretrained_path": "/content/outputs/train/sequential_t1_task48_fft/checkpoints/003000/pretrained_model", | |
| "chunk_size": 50, | |
| "n_action_steps": 50, | |
| "normalization_mapping": { | |
| "VISUAL": "IDENTITY", | |
| "STATE": "MEAN_STD", | |
| "ACTION": "MEAN_STD" | |
| }, | |
| "max_state_dim": 32, | |
| "max_action_dim": 32, | |
| "resize_imgs_with_padding": [ | |
| 512, | |
| 512 | |
| ], | |
| "empty_cameras": 0, | |
| "adapt_to_pi_aloha": false, | |
| "use_delta_joint_actions_aloha": false, | |
| "tokenizer_max_length": 48, | |
| "num_steps": 10, | |
| "use_cache": true, | |
| "freeze_vision_encoder": true, | |
| "train_expert_only": true, | |
| "train_state_proj": true, | |
| "optimizer_lr": 2e-05, | |
| "optimizer_betas": [ | |
| 0.9, | |
| 0.95 | |
| ], | |
| "optimizer_eps": 1e-08, | |
| "optimizer_weight_decay": 0.01, | |
| "optimizer_grad_clip_norm": 10.0, | |
| "scheduler_warmup_steps": 1000, | |
| "scheduler_decay_steps": 30000, | |
| "scheduler_decay_lr": 2.5e-06, | |
| "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct", | |
| "load_vlm_weights": true, | |
| "add_image_special_tokens": false, | |
| "attention_mode": "cross_attn", | |
| "prefix_length": 0, | |
| "pad_language_to": "max_length", | |
| "num_expert_layers": 0, | |
| "num_vlm_layers": 16, | |
| "self_attn_every_n_layers": 2, | |
| "expert_width_multiplier": 0.75, | |
| "min_period": 0.004, | |
| "max_period": 4.0, | |
| "rtc_config": null, | |
| "compile_model": false, | |
| "compile_mode": "max-autotune" | |
| }, | |
| "output_dir": "outputs/train/sequential_t1_t2_task4818_fft", | |
| "job_name": "sequential_t1_t2_task4818_fft", | |
| "resume": false, | |
| "seed": 42, | |
| "cudnn_deterministic": false, | |
| "num_workers": 4, | |
| "batch_size": 16, | |
| "steps": 3000, | |
| "eval_freq": 0, | |
| "log_freq": 1, | |
| "tolerance_s": 0.0001, | |
| "save_checkpoint": true, | |
| "save_freq": 500, | |
| "use_policy_training_preset": true, | |
| "optimizer": { | |
| "type": "adamw", | |
| "lr": 2e-05, | |
| "weight_decay": 0.01, | |
| "grad_clip_norm": 10.0, | |
| "betas": [ | |
| 0.9, | |
| 0.95 | |
| ], | |
| "eps": 1e-08 | |
| }, | |
| "scheduler": { | |
| "type": "cosine_decay_with_warmup", | |
| "num_warmup_steps": 1000, | |
| "num_decay_steps": 30000, | |
| "peak_lr": 2e-05, | |
| "decay_lr": 2.5e-06 | |
| }, | |
| "eval": { | |
| "n_episodes": 50, | |
| "batch_size": 50, | |
| "use_async_envs": false | |
| }, | |
| "wandb": { | |
| "enable": true, | |
| "disable_artifact": true, | |
| "project": "lerobot-smolvla", | |
| "entity": null, | |
| "notes": null, | |
| "run_id": "dzwcngqh", | |
| "mode": null, | |
| "add_tags": true | |
| }, | |
| "peft": null, | |
| "use_rabc": false, | |
| "rabc_progress_path": null, | |
| "rabc_kappa": 0.01, | |
| "rabc_epsilon": 1e-06, | |
| "rabc_head_mode": "sparse", | |
| "rename_map": {}, | |
| "checkpoint_path": null | |
| } |