{ "dataset": { "repo_id": "robot-learning-group47/eval2_all_prompts_fixed_local", "root": "/data/lerobot_datasets/eval2_all_prompts_fixed", "episodes": [ 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 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, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 226, 227, 228, 229, 230, 231, 232, 233, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 249, 250, 251, 252, 253, 254, 255, 256, 257, 258, 259, 260, 261, 262, 263, 264, 265 ], "image_transforms": { "enable": true, "max_num_transforms": 1, "random_order": false, "tfs": { "brightness": { "weight": 1.0, "type": "ColorJitter", "kwargs": { "brightness": [ 0.85, 1.15 ] } } } }, "revision": null, "use_imagenet_stats": true, "video_backend": "torchcodec", "return_uint8": true, "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": "robot-learning-group47/eval2_fast_smolvla_brightness_40k", "private": null, "tags": null, "license": null, "pretrained_path": "lerobot/smolvla_base", "chunk_size": 20, "n_action_steps": 20, "normalization_mapping": { "VISUAL": "IDENTITY", "STATE": "MEAN_STD", "ACTION": "MEAN_STD" }, "max_state_dim": 32, "max_action_dim": 32, "resize_imgs_with_padding": [ 256, 256 ], "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": 0.0001, "optimizer_grad_clip_norm": 10.0, "scheduler_warmup_steps": 500, "scheduler_decay_steps": 40000, "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": false, "compile_mode": "max-autotune" }, "reward_model": null, "output_dir": "/data/lerobot_outputs/train/eval2_fast_smolvla_brightness_40k", "job_name": "eval2_fast_smolvla_brightness_40k", "resume": false, "seed": 1000, "cudnn_deterministic": false, "num_workers": 8, "batch_size": 64, "prefetch_factor": 4, "persistent_workers": true, "steps": 40000, "eval_freq": 20000, "log_freq": 200, "tolerance_s": 0.0001, "save_checkpoint": true, "save_freq": 2500, "use_policy_training_preset": true, "optimizer": { "type": "adamw", "lr": 0.0001, "weight_decay": 0.0001, "grad_clip_norm": 10.0, "betas": [ 0.9, 0.95 ], "eps": 1e-08 }, "scheduler": { "type": "cosine_decay_with_warmup", "num_warmup_steps": 500, "num_decay_steps": 40000, "peak_lr": 0.0001, "decay_lr": 2.5e-06 }, "eval": { "n_episodes": 50, "batch_size": 8, "use_async_envs": true }, "wandb": { "enable": true, "disable_artifact": false, "project": "lerobot", "entity": null, "notes": null, "run_id": "aqi0v4og", "mode": null, "add_tags": true }, "peft": null, "sample_weighting": null, "rename_map": { "observation.images.front": "observation.images.camera1" }, "checkpoint_path": null }