{ "dataset": { "repo_id": "hbseong/record-stacking-so101", "root": null, "episodes": [ 0, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 15, 17, 18, 19, 20, 21, 23, 24, 25, 26, 27, 28, 29, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 56, 57, 58, 59, 60, 61, 62, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 82, 83, 85, 86, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118 ], "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": "internvla", "n_obs_steps": 1, "input_features": { "observation.state": { "type": "STATE", "shape": [ 6 ] }, "observation.images.top": { "type": "VISUAL", "shape": [ 3, 480, 640 ] }, "observation.images.right": { "type": "VISUAL", "shape": [ 3, 480, 640 ] } }, "output_features": { "action": { "type": "ACTION", "shape": [ 6 ] } }, "device": "cuda", "use_amp": false, "push_to_hub": true, "repo_id": "hbseong/internvla_stacking_so101_baseline", "private": null, "tags": null, "license": null, "pretrained_path": null, "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": [ 448, 448 ], "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": 0.0001, "optimizer_betas": [ 0.9, 0.95 ], "optimizer_eps": 1e-08, "optimizer_weight_decay": 1e-10, "optimizer_grad_clip_norm": 10, "scheduler_warmup_steps": 1000, "scheduler_decay_steps": 30000, "scheduler_decay_lr": 2.5e-06, "vlm_model_name": "OpenGVLab/InternVL3-1B-hf", "load_vlm_weights": true, "add_image_special_tokens": false, "attention_mode": "cross_attn", "prefix_length": -1, "pad_language_to": "longest", "num_expert_layers": -1, "num_vlm_layers": 16, "self_attn_every_n_layers": 2, "expert_width_multiplier": 0.75, "min_period": 0.004, "max_period": 4.0 }, "output_dir": "outputs/train/internvla_stacking_so101_baseline", "job_name": "internvla_stacking_so101_baseline", "resume": false, "seed": 1000, "num_workers": 4, "batch_size": 8, "steps": 100000, "eval_freq": 20000, "log_freq": 200, "save_checkpoint": true, "save_freq": 20000, "use_policy_training_preset": true, "optimizer": { "type": "adamw", "lr": 0.0001, "weight_decay": 1e-10, "grad_clip_norm": 10, "betas": [ 0.9, 0.95 ], "eps": 1e-08 }, "scheduler": { "type": "cosine_decay_with_warmup", "num_warmup_steps": 1000, "num_decay_steps": 30000, "peak_lr": 0.0001, "decay_lr": 2.5e-06 }, "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": "5gi3q25r", "mode": null }, "checkpoint_path": null, "rename_map": {} }