| { |
| "dataset": { |
| "repo_id": "Alkatt/so_101_WhiteBlackCubeToBowl_v2", |
| "root": null, |
| "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", |
| "streaming": false |
| }, |
| "env": null, |
| "policy": { |
| "type": "lavla", |
| "n_obs_steps": 1, |
| "input_features": { |
| "observation.state": { |
| "type": "STATE", |
| "shape": [ |
| 6 |
| ] |
| }, |
| "observation.images.camera1": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 480, |
| 640 |
| ] |
| }, |
| "observation.images.camera2": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 480, |
| 640 |
| ] |
| }, |
| "observation.images.camera3": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 480, |
| 640 |
| ] |
| } |
| }, |
| "output_features": { |
| "action": { |
| "type": "ACTION", |
| "shape": [ |
| 6 |
| ] |
| } |
| }, |
| "device": "cuda", |
| "use_amp": false, |
| "use_peft": false, |
| "push_to_hub": true, |
| "repo_id": "Alkatt/LAVLA_VI_Async_Test_01", |
| "private": null, |
| "tags": null, |
| "license": null, |
| "pretrained_path": null, |
| "s1_only": false, |
| "normalization_mapping": { |
| "VISUAL": "MEAN_STD", |
| "STATE": "MEAN_STD", |
| "ACTION": "MEAN_STD" |
| }, |
| "n_action_steps": 50, |
| "chunk_size": 50, |
| "max_action_dim": 6, |
| "s1_freeze_vision_encoder": true, |
| "s1_image_resolution": [ |
| 256, |
| 256 |
| ], |
| "s1_mlp_dim": 2048, |
| "s1_embedding_dim": 1024, |
| "s1_num_attention_heads": 8, |
| "s1_num_layers": 8, |
| "s1_flow_integration_steps": 10, |
| "s1_efficient_net": "google/efficientnet-b0", |
| "s1_add_action_pos_embeddings": true, |
| "s2_vlm_model": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct", |
| "s2_freeze_vlm": true, |
| "optimizer_lr": 1e-05, |
| "optimizer_weight_decay": 1e-06 |
| }, |
| "output_dir": "outputs/train/LAVLA_VI_Async_Test_01", |
| "job_name": "LAVLA_VI_Async_Test_01", |
| "resume": false, |
| "seed": 1000, |
| "cudnn_deterministic": false, |
| "num_workers": 4, |
| "batch_size": 20, |
| "steps": 10, |
| "eval_freq": 20000, |
| "log_freq": 200, |
| "tolerance_s": 0.0001, |
| "save_checkpoint": true, |
| "save_freq": 20000, |
| "use_policy_training_preset": true, |
| "optimizer": { |
| "type": "adam", |
| "lr": 1e-05, |
| "weight_decay": 1e-06, |
| "grad_clip_norm": 10.0, |
| "betas": [ |
| 0.9, |
| 0.999 |
| ], |
| "eps": 1e-08 |
| }, |
| "scheduler": null, |
| "eval": { |
| "n_episodes": 50, |
| "batch_size": 50, |
| "use_async_envs": false |
| }, |
| "wandb": { |
| "enable": true, |
| "disable_artifact": false, |
| "project": "lerobot", |
| "entity": null, |
| "notes": null, |
| "run_id": "3o3hscjs", |
| "mode": null |
| }, |
| "peft": null, |
| "use_rabc": false, |
| "rabc_progress_path": null, |
| "rabc_kappa": 0.01, |
| "rabc_epsilon": 1e-06, |
| "rabc_head_mode": "sparse", |
| "rename_map": { |
| "observation.images.camera1": "observation.images.camera1", |
| "observation.images.camera2": "observation.images.camera2", |
| "observation.images.camera3": "observation.images.camera3" |
| }, |
| "checkpoint_path": null |
| } |
