| { |
| "dataset": { |
| "repo_id": "RobotLearningVLA/banana_green_bowl_eval1_v2", |
| "root": null, |
| "episodes": null, |
| "image_transforms": { |
| "enable": true, |
| "max_num_transforms": 4, |
| "random_order": false, |
| "tfs": { |
| "brightness": { |
| "weight": 2.0, |
| "type": "ColorJitter", |
| "kwargs": { |
| "brightness": [ |
| 0.6, |
| 1.4 |
| ] |
| } |
| }, |
| "contrast": { |
| "weight": 2.0, |
| "type": "ColorJitter", |
| "kwargs": { |
| "contrast": [ |
| 0.6, |
| 1.4 |
| ] |
| } |
| }, |
| "saturation": { |
| "weight": 1.0, |
| "type": "ColorJitter", |
| "kwargs": { |
| "saturation": [ |
| 0.5, |
| 1.5 |
| ] |
| } |
| }, |
| "hue": { |
| "weight": 1.0, |
| "type": "ColorJitter", |
| "kwargs": { |
| "hue": [ |
| -0.02, |
| 0.02 |
| ] |
| } |
| }, |
| "sharpness": { |
| "weight": 1.0, |
| "type": "SharpnessJitter", |
| "kwargs": { |
| "sharpness": [ |
| 0.5, |
| 1.5 |
| ] |
| } |
| }, |
| "affine": { |
| "weight": 1.0, |
| "type": "RandomAffine", |
| "kwargs": { |
| "degrees": [ |
| -3.0, |
| 3.0 |
| ], |
| "translate": [ |
| 0.03, |
| 0.03 |
| ] |
| } |
| }, |
| "perspective": { |
| "weight": 1.5, |
| "type": "RandomPerspective", |
| "kwargs": { |
| "distortion_scale": 0.2, |
| "p": 0.5 |
| } |
| }, |
| "resized_crop": { |
| "weight": 1.0, |
| "type": "RandomResizedCrop", |
| "kwargs": { |
| "size": [ |
| 480, |
| 640 |
| ], |
| "scale": [ |
| 0.75, |
| 1.0 |
| ], |
| "ratio": [ |
| 0.95, |
| 1.05 |
| ] |
| } |
| }, |
| "gaussian_blur": { |
| "weight": 0.5, |
| "type": "GaussianBlur", |
| "kwargs": { |
| "kernel_size": [ |
| 5, |
| 9 |
| ], |
| "sigma": [ |
| 0.3, |
| 2.0 |
| ] |
| } |
| }, |
| "erase": { |
| "weight": 0.5, |
| "type": "RandomErasing", |
| "kwargs": { |
| "p": 0.3, |
| "scale": [ |
| 0.02, |
| 0.1 |
| ] |
| } |
| } |
| } |
| }, |
| "revision": null, |
| "use_imagenet_stats": true, |
| "video_backend": "torchcodec", |
| "return_uint8": false, |
| "streaming": false |
| }, |
| "env": null, |
| "policy": { |
| "type": "smolvla", |
| "n_obs_steps": 1, |
| "input_features": { |
| "observation.state": { |
| "type": "STATE", |
| "shape": [ |
| 6 |
| ] |
| }, |
| "observation.images.camera1": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 256, |
| 256 |
| ] |
| }, |
| "observation.images.camera2": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 256, |
| 256 |
| ] |
| }, |
| "observation.images.camera3": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 256, |
| 256 |
| ] |
| }, |
| "observation.images.empty_camera_0": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 480, |
| 640 |
| ] |
| }, |
| "observation.images.empty_camera_1": { |
| "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": "yukk1/test_eval1_v2", |
| "private": null, |
| "tags": null, |
| "license": null, |
| "pretrained_path": "lerobot/smolvla_base", |
| "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": 2, |
| "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": 0.0001, |
| "optimizer_betas": [ |
| 0.9, |
| 0.95 |
| ], |
| "optimizer_eps": 1e-08, |
| "optimizer_weight_decay": 1e-10, |
| "optimizer_grad_clip_norm": 10.0, |
| "scheduler_warmup_steps": 1000, |
| "scheduler_decay_steps": 9000, |
| "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": true, |
| "compile_mode": "max-autotune" |
| }, |
| "reward_model": null, |
| "output_dir": "outputs/train/eval1_smolvla_h100", |
| "job_name": "smolvla", |
| "resume": false, |
| "seed": 1000, |
| "cudnn_deterministic": false, |
| "num_workers": 16, |
| "batch_size": 256, |
| "prefetch_factor": 4, |
| "persistent_workers": true, |
| "steps": 10000, |
| "eval_freq": 20000, |
| "log_freq": 25, |
| "tolerance_s": 0.0001, |
| "save_checkpoint": true, |
| "save_freq": 1000, |
| "use_policy_training_preset": true, |
| "optimizer": { |
| "type": "adamw", |
| "lr": 0.0001, |
| "weight_decay": 1e-10, |
| "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": 9000, |
| "peak_lr": 0.0001, |
| "decay_lr": 2.5e-06 |
| }, |
| "eval": { |
| "n_episodes": 50, |
| "batch_size": 11, |
| "use_async_envs": true |
| }, |
| "wandb": { |
| "enable": true, |
| "disable_artifact": false, |
| "project": "smolvla_banana_eval1", |
| "entity": null, |
| "notes": null, |
| "run_id": "eval1_3bowls_h100_bf16", |
| "mode": null, |
| "add_tags": true |
| }, |
| "peft": null, |
| "sample_weighting": null, |
| "rename_map": { |
| "observation.images.front": "observation.images.camera1" |
| }, |
| "checkpoint_path": null |
| } |
