{
    "dataset": {
        "repo_id": "robot-learning-group47/eval2_compositional_augmented",
        "root": "/home/shadeform/.cache/lerobot/robot-learning-group47/eval2_compositional_augmented",
        "episodes": null,
        "image_transforms": {
            "enable": true,
            "max_num_transforms": 3,
            "random_order": false,
            "tfs": {
                "brightness": {
                    "weight": 1.0,
                    "type": "ColorJitter",
                    "kwargs": {
                        "brightness": [
                            0.7,
                            1.3
                        ]
                    }
                },
                "contrast": {
                    "weight": 1.0,
                    "type": "ColorJitter",
                    "kwargs": {
                        "contrast": [
                            0.7,
                            1.3
                        ]
                    }
                },
                "sharpness": {
                    "weight": 0.5,
                    "type": "SharpnessJitter",
                    "kwargs": {
                        "sharpness": [
                            0.5,
                            1.5
                        ]
                    }
                }
            }
        },
        "revision": "main",
        "use_imagenet_stats": true,
        "video_backend": "pyav",
        "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": true,
        "push_to_hub": true,
        "repo_id": "robot-learning-group47/smolvla-eval2-lora-vqa-eval1expert",
        "private": null,
        "tags": null,
        "license": null,
        "pretrained_path": "/home/shadeform/outputs/smolvla-eval2-pathC-init",
        "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": [
            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": false,
        "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": 30000,
        "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"
    },
    "output_dir": "/home/shadeform/outputs/smolvla-eval2-lora-vqa-eval1expert",
    "job_name": "smolvla-eval2-lora-vqa-eval1expert",
    "resume": false,
    "seed": 1000,
    "num_workers": 8,
    "batch_size": 32,
    "steps": 40000,
    "eval_freq": 40000,
    "log_freq": 50,
    "tolerance_s": 0.0001,
    "save_checkpoint": true,
    "save_freq": 2000,
    "use_policy_training_preset": false,
    "optimizer": {
        "type": "adamw",
        "lr": 5e-06,
        "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": 40000,
        "peak_lr": 5e-06,
        "decay_lr": 5e-08
    },
    "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": "6rwjph6b",
        "mode": null
    },
    "peft": {
        "target_modules": "model\\.vlm_with_expert\\.vlm\\.model\\.text_model\\.layers\\.[0-9]+\\.self_attn\\.(q|v)_proj",
        "full_training_modules": [
            "lm_expert",
            "state_proj",
            "action_in_proj",
            "action_out_proj",
            "action_time_mlp_in",
            "action_time_mlp_out"
        ],
        "method_type": "lora",
        "init_type": null,
        "r": 16
    },
    "use_rabc": false,
    "rabc_progress_path": null,
    "rabc_kappa": 0.01,
    "rabc_epsilon": 1e-06,
    "rabc_head_mode": "sparse",
    "rename_map": {
        "observation.images.front": "observation.images.camera1"
    },
    "checkpoint_path": null
}