Upload SmolVLA weights

config.json

@@ -0,0 +1,90 @@
+{
+    "type": "smolvla",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                6
+            ]
+        },
+        "observation.images.camera1": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                600,
+                800
+            ]
+        },
+        "observation.images.camera2": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                600,
+                800
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                6
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "push_to_hub": true,
+    "repo_id": "jackvial/so101_smolvla_pickplaceorangecube_e100_20260108_203916",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": "lerobot/smolvla_base",
+    "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": [
+        512,
+        512
+    ],
+    "empty_cameras": 0,
+    "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": 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
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e06af80748004dd9b026be7195365d32843e9d065fc731284bac71731524ab8d
+size 906712520

policy_postprocessor.json

@@ -0,0 +1,32 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "MEAN_STD",
+          "ACTION": "MEAN_STD"
+        }
+      },
+      "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cpu",
+        "float_dtype": null
+      }
+    }
+  ]
+}

policy_postprocessor_step_0_unnormalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0671a3a48ce13da9ce775dbd43e5de4d6d0fc1d4217604953b6956385e13e73d
+size 7592

policy_preprocessor.json

@@ -0,0 +1,88 @@
+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {
+          "observation.images.side": "observation.images.camera1",
+          "observation.images.top": "observation.images.camera2"
+        }
+      }
+    },
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {}
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "smolvla_new_line_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "tokenizer_processor",
+      "config": {
+        "max_length": 48,
+        "task_key": "task",
+        "padding_side": "right",
+        "padding": "max_length",
+        "truncation": true,
+        "tokenizer_name": "HuggingFaceTB/SmolVLM2-500M-Video-Instruct"
+      }
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cuda",
+        "float_dtype": null
+      }
+    },
+    {
+      "registry_name": "normalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "observation.state": {
+            "type": "STATE",
+            "shape": [
+              6
+            ]
+          },
+          "observation.images.camera1": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              600,
+              800
+            ]
+          },
+          "observation.images.camera2": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              600,
+              800
+            ]
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "MEAN_STD",
+          "ACTION": "MEAN_STD"
+        }
+      },
+      "state_file": "policy_preprocessor_step_6_normalizer_processor.safetensors"
+    }
+  ]
+}

policy_preprocessor_step_6_normalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0671a3a48ce13da9ce775dbd43e5de4d6d0fc1d4217604953b6956385e13e73d
+size 7592

train_config.json

@@ -0,0 +1,314 @@
+{
+    "dataset": {
+        "repo_id": "jackvial/so101_pickplaceorangecube_e100",
+        "root": "/tmp/lerobot_jackvial_so101_pickplaceorangecube_e100",
+        "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": "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,
+                    600,
+                    800
+                ]
+            },
+            "observation.images.camera2": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    600,
+                    800
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    6
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "push_to_hub": true,
+        "repo_id": "jackvial/so101_smolvla_pickplaceorangecube_e100_20260108_203916",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "lerobot/smolvla_base",
+        "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": [
+            512,
+            512
+        ],
+        "empty_cameras": 0,
+        "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": 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
+    },
+    "output_dir": "outputs/train/so101_smolvla_pickplaceorangecube_e100_20260108_203916",
+    "job_name": "smolvla",
+    "resume": false,
+    "seed": 1000,
+    "num_workers": 4,
+    "batch_size": 8,
+    "steps": 100000,
+    "eval_freq": 20000,
+    "log_freq": 10,
+    "save_checkpoint": true,
+    "save_freq": 5000,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 0.0001,
+        "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": 30000,
+        "peak_lr": 0.0001,
+        "decay_lr": 2.5e-06
+    },
+    "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": null,
+        "mode": null
+    },
+    "checkpoint_path": null,
+    "rename_map": {},
+    "validation": {
+        "enable": false,
+        "val_ratio": 0.05,
+        "val_freq": 100,
+        "val_batch_size": 8,
+        "save_split": true,
+        "task_based_split": {
+            "enable_task_based_split": true,
+            "task_keywords": {
+                "left": [
+                    "left",
+                    "leftward",
+                    "to the left"
+                ],
+                "right": [
+                    "right",
+                    "rightward",
+                    "to the right"
+                ],
+                "center": [
+                    "center",
+                    "central",
+                    "middle",
+                    "centered"
+                ]
+            },
+            "split_strategy": "balanced",
+            "val_ratio": 0.2,
+            "fallback_to_random": true,
+            "case_sensitive": false,
+            "min_episodes_per_keyword": 2
+        },
+        "oversampling": {
+            "enable_oversampling": false,
+            "target_strategy": "max_class",
+            "target_episodes_per_keyword": null,
+            "custom_targets": null,
+            "oversampling_method": "weighted_sampling",
+            "apply_to": "train_only",
+            "min_original_episodes": 5,
+            "max_oversample_ratio": 10.0,
+            "frame_level_oversampling": true
+        },
+        "n_val_steps": 100,
+        "enable_per_variation_metrics": true,
+        "min_episodes_per_variation": 1
+    },
+    "metrics_logging": {
+        "wandb_project": "assembler0-training",
+        "wandb_mode": "online",
+        "wandb_upload_checkpoints": true
+    },
+    "augmentation": {
+        "enable": false,
+        "rotation_degrees": [
+            -1,
+            1
+        ],
+        "distortion_scale": 0.1,
+        "scale_range": [
+            0.9,
+            1.1
+        ],
+        "brightness": [
+            0.7,
+            1.5
+        ],
+        "contrast": [
+            0.8,
+            1.2
+        ],
+        "hue": [
+            -0.1,
+            0.1
+        ],
+        "saturation": [
+            0.8,
+            1.2
+        ],
+        "probability": 0.25,
+        "same_on_frame": true,
+        "same_on_batch": true,
+        "data_format": "BTCHW",
+        "image_keys": [
+            "observation.images.camera1",
+            "observation.images.camera2"
+        ]
+    },
+    "camera": {
+        "enable_remap": true,
+        "enable_alias": false
+    },
+    "debug_episodes": false,
+    "local_mode": true,
+    "log_camera_frames": false
+}