{
    "type": "mtdit_spatial",
    "n_obs_steps": 2,
    "input_features": {
        "observation.state": {
            "type": "STATE",
            "shape": [
                13
            ]
        },
        "observation.images.left": {
            "type": "VISUAL",
            "shape": [
                3,
                480,
                640
            ]
        },
        "observation.images.right": {
            "type": "VISUAL",
            "shape": [
                3,
                480,
                640
            ]
        },
        "observation.images.wrist": {
            "type": "VISUAL",
            "shape": [
                3,
                480,
                640
            ]
        },
        "observation.base_pose": {
            "type": "STATE",
            "shape": [
                3
            ]
        },
        "observation.eef_state": {
            "type": "STATE",
            "shape": [
                13
            ]
        }
    },
    "output_features": {
        "action": {
            "type": "ACTION",
            "shape": [
                13
            ]
        },
        "action.eef": {
            "type": "ACTION",
            "shape": [
                13
            ]
        }
    },
    "device": "cuda",
    "use_amp": false,
    "use_peft": false,
    "push_to_hub": false,
    "repo_id": null,
    "private": null,
    "tags": null,
    "license": null,
    "pretrained_path": null,
    "pretrained_revision": null,
    "horizon": 32,
    "n_action_steps": 24,
    "objective": "diffusion",
    "noise_scheduler_type": "DDPM",
    "num_train_timesteps": 100,
    "beta_schedule": "squaredcos_cap_v2",
    "beta_start": 0.0001,
    "beta_end": 0.02,
    "prediction_type": "epsilon",
    "clip_sample": true,
    "clip_sample_range": 1.0,
    "num_inference_steps": null,
    "sigma_min": 0.0,
    "num_integration_steps": 100,
    "integration_method": "euler",
    "timestep_sampling_strategy": "beta",
    "timestep_sampling_s": 0.999,
    "timestep_sampling_alpha": 1.5,
    "timestep_sampling_beta": 1.0,
    "hidden_dim": 512,
    "num_layers": 4,
    "num_heads": 8,
    "dropout": 0.1,
    "use_positional_encoding": false,
    "timestep_embed_dim": 256,
    "use_rope": true,
    "rope_base": 10000.0,
    "vision_encoder_name": "openai/clip-vit-base-patch16",
    "use_separate_rgb_encoder_per_camera": false,
    "vision_encoder_lr_multiplier": 0.1,
    "image_resize_shape": [
        240,
        320
    ],
    "image_crop_shape": [
        224,
        224
    ],
    "image_crop_is_random": true,
    "vision_feature_mode": "cls",
    "num_spatial_keypoints": 32,
    "spatial_softmax_keep_cls": true,
    "spatial_softmax_learnable_temperature": true,
    "cross_attention_heads": null,
    "action_stride": 1,
    "state_dropout_prob": 0.0,
    "action_loss_weighting": "none",
    "loss_weight_max": 4.0,
    "loss_gripper_dim": 9,
    "state_conditioning": "full",
    "state_feature_names": null,
    "masked_state_names": null,
    "use_relative_actions": true,
    "relative_exclude_joints": [
        "gripper"
    ],
    "action_feature_names": [
        "eef_x",
        "eef_y",
        "eef_z",
        "eef_xx",
        "eef_xy",
        "eef_xz",
        "eef_yx",
        "eef_yy",
        "eef_yz",
        "gripper",
        "base_x",
        "base_y",
        "base_yaw"
    ],
    "text_encoder_name": "openai/clip-vit-base-patch16",
    "tokenizer_max_length": 77,
    "tokenizer_padding": "max_length",
    "tokenizer_padding_side": "right",
    "tokenizer_truncation": true,
    "normalization_mapping": {
        "VISUAL": "MEAN_STD",
        "STATE": "MIN_MAX",
        "ACTION": "QUANTILES"
    },
    "optimizer_lr": 0.0003,
    "optimizer_betas": [
        0.95,
        0.999
    ],
    "optimizer_eps": 1e-08,
    "optimizer_weight_decay": 0.0,
    "scheduler_name": "cosine",
    "scheduler_warmup_steps": 0,
    "do_mask_loss_for_padding": false,
    "drop_n_last_frames": 7
}