Robotics
LeRobot
Safetensors
English
fineart-vla
vision-language-action
bimanual-manipulation
subtask-prediction
imitation-learning
Instructions to use lerobot/FineART-VLA-subtask-midtrained with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use lerobot/FineART-VLA-subtask-midtrained with LeRobot:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download train_config.json from lerobot/FineART-VLA-subtask-midtrained: direct link, hf CLI and curl.
- Browser
- Download file 9.25 kB
-
https://huggingface.co/lerobot/FineART-VLA-subtask-midtrained/resolve/main/train_config.json
- Command line
-
hf download hf://lerobot/FineART-VLA-subtask-midtrained/train_config.json
-
curl -L -o train_config.json https://huggingface.co/lerobot/FineART-VLA-subtask-midtrained/resolve/main/train_config.json
9.25 kB
| { | |
| "dataset": { | |
| "repo_id": "scale/scale_1kots_lerobot_v3", | |
| "root": "/opt/dlami/nvme/jade/scale_1kots_lerobot_v3", | |
| "episodes": null, | |
| "exclude_episodes": [ | |
| 40523, | |
| 40524, | |
| 40526, | |
| 40527, | |
| 40530, | |
| 40531, | |
| 40532 | |
| ], | |
| "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, | |
| "sampling_index_path": "auto", | |
| "sampling_alpha": 0.5 | |
| }, | |
| "env": null, | |
| "policy": { | |
| "type": "fineart_vla", | |
| "n_obs_steps": 1, | |
| "input_features": { | |
| "observation.state": { | |
| "type": "STATE", | |
| "shape": [ | |
| 14 | |
| ] | |
| }, | |
| "observation.images.cam_high": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 3, | |
| 360, | |
| 640 | |
| ] | |
| }, | |
| "observation.images.cam_left_wrist": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 3, | |
| 360, | |
| 640 | |
| ] | |
| }, | |
| "observation.images.cam_right_wrist": { | |
| "type": "VISUAL", | |
| "shape": [ | |
| 3, | |
| 360, | |
| 640 | |
| ] | |
| } | |
| }, | |
| "output_features": { | |
| "action": { | |
| "type": "ACTION", | |
| "shape": [ | |
| 14 | |
| ] | |
| } | |
| }, | |
| "device": "cuda", | |
| "use_amp": false, | |
| "use_peft": false, | |
| "push_to_hub": false, | |
| "repo_id": null, | |
| "private": null, | |
| "tags": null, | |
| "license": null, | |
| "pretrained_path": "lerobot/pi052_base", | |
| "pretrained_revision": null, | |
| "paligemma_variant": "gemma_2b", | |
| "action_expert_variant": "gemma_300m", | |
| "dtype": "bfloat16", | |
| "chunk_size": 50, | |
| "n_action_steps": 50, | |
| "max_state_dim": 32, | |
| "max_action_dim": 32, | |
| "num_inference_steps": 10, | |
| "time_sampling_beta_alpha": 1.5, | |
| "time_sampling_beta_beta": 1.0, | |
| "time_sampling_scale": 0.999, | |
| "time_sampling_offset": 0.001, | |
| "min_period": 0.004, | |
| "max_period": 4.0, | |
| "use_relative_actions": false, | |
| "relative_exclude_joints": [ | |
| "gripper" | |
| ], | |
| "action_feature_names": [ | |
| "left_shoulder_pan", | |
| "left_shoulder_lift", | |
| "left_elbow_flex", | |
| "left_wrist_angle", | |
| "left_wrist_rotate", | |
| "left_gripper", | |
| "left_gripper_finger", | |
| "right_shoulder_pan", | |
| "right_shoulder_lift", | |
| "right_elbow_flex", | |
| "right_wrist_angle", | |
| "right_wrist_rotate", | |
| "right_gripper", | |
| "right_gripper_finger" | |
| ], | |
| "rtc_config": null, | |
| "image_resolution": [ | |
| 224, | |
| 224 | |
| ], | |
| "empty_cameras": 0, | |
| "tokenizer_max_length": 128, | |
| "normalization_mapping": { | |
| "VISUAL": "IDENTITY", | |
| "STATE": "QUANTILES", | |
| "ACTION": "QUANTILES" | |
| }, | |
| "gradient_checkpointing": true, | |
| "compile_model": true, | |
| "compile_mode": "default", | |
| "freeze_vision_encoder": false, | |
| "train_expert_only": false, | |
| "optimizer_lr": 2.5e-05, | |
| "optimizer_betas": [ | |
| 0.9, | |
| 0.95 | |
| ], | |
| "optimizer_eps": 1e-08, | |
| "optimizer_weight_decay": 1e-10, | |
| "optimizer_grad_clip_norm": 1.0, | |
| "scheduler_warmup_steps": 2000, | |
| "scheduler_decay_steps": 300000, | |
| "scheduler_decay_lr": 5e-06, | |
| "recipe_path": "recipes/subtask.yaml", | |
| "text_loss_weight": 1.0, | |
| "flow_loss_weight": 10.0, | |
| "unfreeze_lm_head": true, | |
| "enable_fast_action_loss": true, | |
| "action_tokenizer_name": "lerobot/fast-action-tokenizer", | |
| "max_action_tokens": 384, | |
| "fast_skip_tokens": 128, | |
| "fast_action_loss_weight": 1.0, | |
| "auto_fit_fast_tokenizer": true, | |
| "fast_tokenizer_cache_dir": "~/.cache/lerobot/fast_tokenizers", | |
| "fast_tokenizer_fit_samples": 16384, | |
| "fast_tokenizer_validation_samples": 256, | |
| "fast_tokenizer_max_reconstruction_rmse": 0.1, | |
| "fast_tokenizer_max_dim_rmse": 0.2, | |
| "knowledge_insulation": true, | |
| "use_flashrt_adarms": false, | |
| "use_compiled_text_ce": true, | |
| "use_compiled_vision": false, | |
| "use_flex_attention": false, | |
| "use_manual_attention": false, | |
| "manual_attention_scope": "all", | |
| "lm_head_lr_scale": 1.0, | |
| "backbone_lr_scale": 1.0, | |
| "action_expert_lr_scale": 1.0, | |
| "flow_num_repeats": 1, | |
| "text_ce_z_loss_weight": 0.0001, | |
| "optimizer_foreach": false, | |
| "optimizer_fused": true | |
| }, | |
| "reward_model": null, | |
| "output_dir": "/opt/dlami/nvme/jade/runs/pi052_subgoal_3cam_14d_balanced", | |
| "job_name": "pi052_subgoal_3cam_14d_balanced", | |
| "resume": false, | |
| "seed": 1000, | |
| "cudnn_deterministic": false, | |
| "num_workers": 12, | |
| "batch_size": 8, | |
| "prefetch_factor": 4, | |
| "persistent_workers": true, | |
| "dataloader_multiprocessing_context": "fork", | |
| "steps": 300000, | |
| "env_eval_freq": 0, | |
| "log_freq": 50, | |
| "eval_steps": 0, | |
| "max_eval_samples": 0, | |
| "tolerance_s": 0.0001, | |
| "save_checkpoint": true, | |
| "save_freq": 2500, | |
| "use_policy_training_preset": true, | |
| "optimizer": { | |
| "type": "adamw", | |
| "lr": 2.5e-05, | |
| "weight_decay": 1e-10, | |
| "grad_clip_norm": 1.0, | |
| "betas": [ | |
| 0.9, | |
| 0.95 | |
| ], | |
| "eps": 1e-08, | |
| "foreach": false, | |
| "fused": true, | |
| "master_weights": true, | |
| "conditioner_weight_decay": 0.0, | |
| "probe_log_every": 500 | |
| }, | |
| "scheduler": { | |
| "type": "cosine_decay_with_warmup", | |
| "num_warmup_steps": 2000, | |
| "num_decay_steps": 300000, | |
| "peak_lr": 2.5e-05, | |
| "decay_lr": 5e-06 | |
| }, | |
| "eval": { | |
| "n_episodes": 50, | |
| "batch_size": 50, | |
| "use_async_envs": true, | |
| "recording": false, | |
| "recording_repo_id": null, | |
| "recording_private": false | |
| }, | |
| "wandb": { | |
| "enable": true, | |
| "disable_artifact": true, | |
| "project": "pi052-scaletrain", | |
| "entity": null, | |
| "notes": null, | |
| "run_id": "u7jxsy4l", | |
| "mode": "offline", | |
| "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 | |
| } | |