TimR643/sorting_algorithm_cubes

1{2    "type": "smolvla",3    "n_obs_steps": 1,4    "input_features": {5        "observation.state": {6            "type": "STATE",7            "shape": [8                89            ]10        },11        "observation.images.camera1": {12            "type": "VISUAL",13            "shape": [14                3,15                256,16                25617            ]18        },19        "observation.images.camera2": {20            "type": "VISUAL",21            "shape": [22                3,23                256,24                25625            ]26        },27        "observation.images.camera3": {28            "type": "VISUAL",29            "shape": [30                3,31                256,32                25633            ]34        }35    },36    "output_features": {37        "action": {38            "type": "ACTION",39            "shape": [40                841            ]42        }43    },44    "device": "cuda",45    "use_amp": false,46    "use_peft": false,47    "push_to_hub": true,48    "repo_id": "TimR643/sorting_algorithm_cubes",49    "private": null,50    "tags": null,51    "license": null,52    "pretrained_path": "lerobot/smolvla_base",53    "chunk_size": 50,54    "n_action_steps": 50,55    "normalization_mapping": {56        "VISUAL": "IDENTITY",57        "STATE": "MEAN_STD",58        "ACTION": "MEAN_STD"59    },60    "max_state_dim": 32,61    "max_action_dim": 32,62    "resize_imgs_with_padding": [63        512,64        51265    ],66    "empty_cameras": 0,67    "adapt_to_pi_aloha": false,68    "use_delta_joint_actions_aloha": false,69    "tokenizer_max_length": 48,70    "num_steps": 10,71    "use_cache": true,72    "freeze_vision_encoder": true,73    "train_expert_only": true,74    "train_state_proj": true,75    "optimizer_lr": 0.0001,76    "optimizer_betas": [77        0.9,78        0.9579    ],80    "optimizer_eps": 1e-08,81    "optimizer_weight_decay": 1e-10,82    "optimizer_grad_clip_norm": 10.0,83    "scheduler_warmup_steps": 1000,84    "scheduler_decay_steps": 30000,85    "scheduler_decay_lr": 2.5e-06,86    "vlm_model_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct",87    "load_vlm_weights": true,88    "add_image_special_tokens": false,89    "attention_mode": "cross_attn",90    "prefix_length": 0,91    "pad_language_to": "max_length",92    "num_expert_layers": 0,93    "num_vlm_layers": 16,94    "self_attn_every_n_layers": 2,95    "expert_width_multiplier": 0.75,96    "min_period": 0.004,97    "max_period": 4.0,98    "rtc_config": null,99    "compile_model": false,100    "compile_mode": "max-autotune"101}