| { |
| "dataset": { |
| "repo_id": "maximellerbach/omx_multicubes", |
| "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": false, |
| "video_backend": "pyav", |
| "return_uint8": false, |
| "streaming": false |
| }, |
| "env": null, |
| "policy": { |
| "type": "lingbot_va", |
| "n_obs_steps": 1, |
| "input_features": { |
| "observation.images.cam_high": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 256, |
| 256 |
| ] |
| }, |
| "observation.images.cam_left_wrist": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 256, |
| 256 |
| ] |
| }, |
| "observation.images.cam_right_wrist": { |
| "type": "VISUAL", |
| "shape": [ |
| 3, |
| 256, |
| 256 |
| ] |
| } |
| }, |
| "output_features": { |
| "action": { |
| "type": "ACTION", |
| "shape": [ |
| 6 |
| ] |
| } |
| }, |
| "device": "cuda", |
| "use_amp": false, |
| "use_peft": false, |
| "push_to_hub": true, |
| "repo_id": "maximellerbach/omx_multicubes_lingbot_va", |
| "private": null, |
| "tags": null, |
| "license": null, |
| "pretrained_path": "lerobot/lingbot_va_base", |
| "pretrained_revision": null, |
| "patch_size": [ |
| 1, |
| 2, |
| 2 |
| ], |
| "num_attention_heads": 24, |
| "attention_head_dim": 128, |
| "in_channels": 48, |
| "out_channels": 48, |
| "action_dim": 30, |
| "text_dim": 4096, |
| "freq_dim": 256, |
| "ffn_dim": 14336, |
| "num_layers": 30, |
| "cross_attn_norm": true, |
| "eps": 1e-06, |
| "rope_max_seq_len": 1024, |
| "attn_mode": "flex", |
| "wan_pretrained_path": "robbyant/lingbot-va-base", |
| "dtype": "bfloat16", |
| "text_encoder_device": "cuda", |
| "obs_cam_keys": [ |
| "observation.images.cam_high", |
| "observation.images.cam_left_wrist" |
| ], |
| "image_hflip": false, |
| "camera_layout": "width_concat", |
| "height": 256, |
| "width": 320, |
| "action_per_frame": 16, |
| "frame_chunk_size": 2, |
| "attn_window": 72, |
| "num_inference_steps": 25, |
| "video_exec_step": -1, |
| "action_num_inference_steps": 50, |
| "guidance_scale": 5.0, |
| "action_guidance_scale": 1.0, |
| "snr_shift": 5.0, |
| "action_snr_shift": 1.0, |
| "max_sequence_length": 512, |
| "used_action_channel_ids": [ |
| 0, |
| 1, |
| 2, |
| 3, |
| 4, |
| 5 |
| ], |
| "save_predicted_video": false, |
| "normalization_mapping": { |
| "VISUAL": "IDENTITY", |
| "STATE": "IDENTITY", |
| "ACTION": "QUANTILES" |
| }, |
| "optimizer_lr": 1e-05, |
| "optimizer_betas": [ |
| 0.9, |
| 0.95 |
| ], |
| "optimizer_eps": 1e-08, |
| "optimizer_weight_decay": 0.0001, |
| "optimizer_grad_clip_norm": 1.0, |
| "scheduler_warmup_steps": 1000 |
| }, |
| "reward_model": null, |
| "output_dir": "outputs/train/omx_multicubes_lingbot_full", |
| "job_name": "lingbot_va", |
| "resume": false, |
| "seed": 1000, |
| "cudnn_deterministic": false, |
| "num_workers": 8, |
| "batch_size": 8, |
| "prefetch_factor": 4, |
| "persistent_workers": true, |
| "steps": 10000, |
| "eval_freq": 20000, |
| "log_freq": 50, |
| "tolerance_s": 0.0001, |
| "save_checkpoint": true, |
| "save_freq": 5000, |
| "use_policy_training_preset": true, |
| "optimizer": { |
| "type": "adamw", |
| "lr": 1e-05, |
| "weight_decay": 0.0001, |
| "grad_clip_norm": 1.0, |
| "betas": [ |
| 0.9, |
| 0.95 |
| ], |
| "eps": 1e-08 |
| }, |
| "scheduler": { |
| "type": "constant_with_warmup", |
| "num_warmup_steps": 1000 |
| }, |
| "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": "lerobot", |
| "entity": null, |
| "notes": null, |
| "run_id": "1cfabfgc", |
| "mode": null, |
| "add_tags": true |
| }, |
| "peft": null, |
| "sample_weighting": null, |
| "rename_map": { |
| "observation.images.top": "observation.images.cam_high", |
| "observation.images.wrist": "observation.images.cam_left_wrist" |
| }, |
| "checkpoint_path": null |
| } |
