{ "dataset": { "repo_id": "Dicomsky/human_inloop_grasp", "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 }, "value": { "type": "pistar06", "n_obs_steps": 1, "input_features": { "observation.state": { "type": "STATE", "shape": [ 6 ] }, "observation.images.top": { "type": "VISUAL", "shape": [ 3, 480, 640 ] }, "observation.images.wrist": { "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": "Dicomsky/value_human_inloop_grasp", "private": null, "tags": null, "license": null, "pretrained_path": null, "vision_repo_id": "google/siglip-so400m-patch14-384", "language_repo_id": "google/gemma-3-270m", "vision_revision": null, "language_revision": null, "task_field": "task", "camera_features": [], "state_feature": "observation.state", "include_state_in_prompt": true, "max_state_dim": 32, "state_discretization_bins": 256, "target_key": "observation.value_target", "loss_weight_key": "observation.value_loss_weight", "task_index_feature": "task_index", "tokenizer_max_length": 200, "state_proj_dim": 512, "fusion_hidden_dim": 512, "fusion_num_layers": 2, "fusion_num_heads": 8, "num_bins": 201, "bin_min": -1.0, "bin_max": 0.0, "dropout": 0.1, "dtype": "bfloat16", "freeze_vision_encoder": true, "freeze_language_model": true, "use_gradient_checkpointing": false, "optimizer_lr": 5e-05, "optimizer_weight_decay": 1e-05, "optimizer_grad_clip_norm": 10.0, "scheduler_warmup_steps": 500, "scheduler_decay_steps": 8000, "scheduler_decay_lr": 1e-06, "normalization_mapping": { "VISUAL": "IDENTITY", "STATE": "QUANTILES", "ACTION": "IDENTITY" } }, "env": null, "output_dir": "outputs/value_train/human_inloop_grasp", "job_name": "human_inloop_grasp", "resume": false, "seed": 1000, "num_workers": 4, "batch_size": 16, "steps": 8000, "log_freq": 200, "tolerance_s": 0.0001, "save_checkpoint": true, "save_freq": 4000, "use_value_training_preset": true, "use_policy_training_preset": true, "optimizer": { "type": "adamw", "lr": 5e-05, "weight_decay": 1e-05, "grad_clip_norm": 10.0, "betas": [ 0.9, 0.999 ], "eps": 1e-08 }, "scheduler": { "type": "cosine_decay_with_warmup", "num_warmup_steps": 500, "num_decay_steps": 8000, "peak_lr": 5e-05, "decay_lr": 1e-06 }, "targets": { "success_field": "episode_success", "default_success": "failure", "c_fail_coef": 1.0, "target_field": "observation.value_target" }, "wandb": { "enable": true, "disable_artifact": false, "project": "lerobot", "entity": null, "notes": null, "run_id": "yf2b7ime", "mode": null }, "peft": null, "rename_map": {}, "checkpoint_path": null }