Add files using upload-large-folder tool

Browse files

Files changed (8) hide show

README.md +86 -0
config.json +107 -0
model.safetensors +3 -0
policy_postprocessor.json +38 -0
policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
policy_preprocessor.json +96 -0
policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
train_config.json +250 -0

README.md ADDED Viewed

	@@ -0,0 +1,86 @@

+---
+license: apache-2.0
+library_name: lerobot
+pipeline_tag: robotics
+base_model: CoRL2026-CSI/smolvla_isaaclab_so101_11task_basecap_3300epi_8ep
+datasets:
+- CoRL2026-CSI/SO101-cap_close_pot_10fps
+tags:
+- lerobot
+- robotics
+- smolvla
+- vla
+- so101
+- code-as-policies
+- cap
+- imitation-learning
+- 50epochs
+- single-arm
+- dual-camera
+- close-pot
+- close-pot-lid
+- pot-lid
+---
+# SmolVLA-CaP-ClosePot-50epochs
+This repository contains a SmolVLA policy fine-tuned with LeRobot for the SO101 CAP task **Close Pot Lid**. The policy was initialized from `CoRL2026-CSI/smolvla_isaaclab_so101_11task_basecap_3300epi_8ep` and trained for 50 epochs on `CoRL2026-CSI/SO101-cap_close_pot_10fps`.
+## Model Details
+| Field | Value |
+|---|---|
+| Policy type | `smolvla` |
+| Task | close the pot lid in a tabletop SO101 manipulation setup |
+| Robot | SO101 follower |
+| Dataset | `CoRL2026-CSI/SO101-cap_close_pot_10fps` |
+| Base model | `CoRL2026-CSI/smolvla_isaaclab_so101_11task_basecap_3300epi_8ep` |
+| Training steps | `7400` |
+| Completed step | `7400` |
+| Batch size | `128` per GPU |
+| Effective batch size | `256` |
+| Action chunk size | `50` |
+| Action horizon | `50` |
+| Observation steps | `1` |
+| Inference denoising steps | `50` |
+| Model weights | `model.safetensors` (864.7 MiB) |
+## Training Setup
+The run used two CUDA processes with `batch_size=128` per process, image augmentation enabled, and camera key remapping from the dataset's raw cameras to the SmolVLA camera names:
+```text
+observation.images.left_wrist -> observation.images.camera1
+observation.images.top        -> observation.images.camera2
+```
+The checkpoint was saved locally at step `7400` with LeRobot's preprocessor and postprocessor artifacts included in this repository.
+## Files
+```text
+model.safetensors
+config.json
+train_config.json
+policy_preprocessor.json
+policy_preprocessor_step_5_normalizer_processor.safetensors
+policy_postprocessor.json
+policy_postprocessor_step_0_unnormalizer_processor.safetensors
+```
+## Usage
+```python
+from lerobot.policies.smolvla.modeling_smolvla import SmolVLAPolicy
+policy = SmolVLAPolicy.from_pretrained("CoRL2026-CSI/SmolVLA-CaP-ClosePot-50epochs")
+```
+For robot deployment, use the same camera mapping, normalization pipeline, and SO101 action/state conventions used by the training dataset.
+## Intended Use
+This model is intended for imitation-learning experiments and SO101 tabletop manipulation research on the specified CAP task. It is not a general-purpose robot policy and should be validated in a controlled workspace before any hardware deployment.
+## Limitations
+The model was trained on a single task dataset with fixed camera views, object set, action space, and workspace assumptions. No official evaluation success rate is included in this repository.

config.json ADDED Viewed

	@@ -0,0 +1,107 @@

+{
+    "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
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                6
+            ]
+        },
+        "action.radian_urdf0": {
+            "type": "ACTION",
+            "shape": [
+                6
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": false,
+    "push_to_hub": false,
+    "repo_id": null,
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": "CoRL2026-CSI/smolvla_isaaclab_so101_11task_basecap_3300epi_8ep",
+    "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": 50,
+    "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,
+    "compile_model": false,
+    "compile_mode": "max-autotune"
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d158d18cdaa213ab62766697ec25c797a496f785520cb8765a89a398d13269
+size 906712520

policy_postprocessor.json ADDED Viewed

	@@ -0,0 +1,38 @@

+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ]
+          },
+          "action.radian_urdf0": {
+            "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 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5159f7791572af0fcc14087b87a97af2f8657edfccf8b12e176891b479007d
+size 16796

policy_preprocessor.json ADDED Viewed

	@@ -0,0 +1,96 @@

+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {
+          "observation.images.left_wrist": "observation.images.camera1",
+          "observation.images.top": "observation.images.camera2"
+        }
+      }
+    },
+    {
+      "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,
+              256,
+              256
+            ]
+          },
+          "observation.images.camera2": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              256,
+              256
+            ]
+          },
+          "observation.images.camera3": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              256,
+              256
+            ]
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ]
+          },
+          "action.radian_urdf0": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "IDENTITY",
+          "STATE": "MEAN_STD",
+          "ACTION": "MEAN_STD"
+        }
+      },
+      "state_file": "policy_preprocessor_step_5_normalizer_processor.safetensors"
+    }
+  ]
+}

policy_preprocessor_step_5_normalizer_processor.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5159f7791572af0fcc14087b87a97af2f8657edfccf8b12e176891b479007d
+size 16796

train_config.json ADDED Viewed

	@@ -0,0 +1,250 @@

+{
+    "dataset": {
+        "repo_id": "CoRL2026-CSI/SO101-cap_close_pot_10fps",
+        "root": null,
+        "episodes": null,
+        "image_transforms": {
+            "enable": true,
+            "max_num_transforms": 3,
+            "random_order": true,
+            "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
+    },
+    "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
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    6
+                ]
+            },
+            "action.radian_urdf0": {
+                "type": "ACTION",
+                "shape": [
+                    6
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": false,
+        "push_to_hub": false,
+        "repo_id": null,
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "CoRL2026-CSI/smolvla_isaaclab_so101_11task_basecap_3300epi_8ep",
+        "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": 50,
+        "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,
+        "compile_model": false,
+        "compile_mode": "max-autotune"
+    },
+    "output_dir": "/data/vpraise-corl/workspace/AutoDataCollector/outputs/train/cap_smolvla_close_pot",
+    "job_name": "cap_smolvla_close_pot",
+    "resume": false,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "num_workers": 6,
+    "persistent_workers": true,
+    "dataloader_prefetch_factor": 2,
+    "batch_size": 128,
+    "gradient_accumulation_steps": 1,
+    "steps": 7400,
+    "eval_freq": 0,
+    "log_freq": 100,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 7400,
+    "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-smolvla-cap",
+        "entity": null,
+        "notes": null,
+        "run_id": "7vjw46kw",
+        "mode": null
+    },
+    "peft": null,
+    "use_rabc": false,
+    "rabc_progress_path": null,
+    "rabc_kappa": 0.01,
+    "rabc_epsilon": 1e-06,
+    "rabc_head_mode": "sparse",
+    "rename_map": {
+        "observation.images.left_wrist": "observation.images.camera1",
+        "observation.images.top": "observation.images.camera2"
+    },
+    "checkpoint_path": null
+}