ACT right-arm cup grasp, step 160001211111

Browse files

Files changed (11) hide show

README.md +33 -0
config.json +102 -0
model.safetensors +3 -0
policy_postprocessor.json +32 -0
policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
policy_preprocessor.json +94 -0
policy_preprocessor_step_5_normalizer_processor.safetensors +3 -0
tokenizer/chat_template.jinja +2 -0
tokenizer/tokenizer.json +0 -0
tokenizer/tokenizer_config.json +27 -0
train_config.json +309 -0

README.md ADDED Viewed

	@@ -0,0 +1,33 @@

+---
+tags: [robotics, lerobot, act, xlerobot, bimanual]
+library_name: lerobot
+pipeline_tag: robotics
+license: apache-2.0
+---
+# ACT — right-arm cup grasp (XLeRobot)
+Trained with [LeRobot](https://github.com/huggingface/lerobot) ACT on
+[`Suyang99/xlerobot-cup-grasp-20260820-0230`](https://huggingface.co/datasets/Suyang99/xlerobot-cup-grasp-20260820-0230).
+| | |
+|---|---|
+| Task | Pick up the cup and place it down — **right arm only** (`arms: 1.0`) |
+| Dataset | 50 episodes / 19,453 frames / 30 fps, 5 cup positions |
+| Policy | ACT, 51.6 M parameters |
+| Checkpoint | **step 160001211111** of 20,000 |
+| Trained on | Jetson Orin Nano Super (8 GB unified), torch 2.8.0, batch size 2 |
+| Cameras | head, left_arm_wrist, right_arm_wrist |
+| Action / state | 17-dim (left arm 6 · right arm 6 · head 2 · base 3) |
+## Important: the left arm is parked in this data
+Dimensions 0–5 (the left arm) hold a single constant across every frame — the recording ran with
+`arms: 1.0`, so the left arm never followed the operator. **This policy therefore cannot drive the
+left arm**, and it will not transfer to a left-arm version of the task. A bimanual task needs its
+own recording with `arms: 0.0`.
+## Hardware caveat
+The gripper is being replaced (Fin-Ray blade 68 mm → 90 mm). Once that lands, the arm's dynamics
+change and this checkpoint's real-world behaviour has to be re-measured.

config.json ADDED Viewed

	@@ -0,0 +1,102 @@

+{
+    "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": [
+                17
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": false,
+    "push_to_hub": false,
+    "repo_id": null,
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": "lerobot/smolvla_base",
+    "pretrained_revision": null,
+    "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,
+    "compile_model": false,
+    "compile_mode": "max-autotune"
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:62741bb31447a775966492f5f06e05af16e6b9c3d8ed3c06475a54797afe41d1
+size 906712552

policy_postprocessor.json ADDED Viewed

	@@ -0,0 +1,32 @@

+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              17
+            ]
+          }
+        },
+        "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 sha256:76228b12797e83b471eca7f1543770265c661f81752355a30f826976a6867d61
+size 9608

policy_preprocessor.json ADDED Viewed

	@@ -0,0 +1,94 @@

+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {
+          "observation.images.head": "observation.images.camera1",
+          "observation.images.right_arm_wrist": "observation.images.camera2",
+          "observation.images.left_arm_wrist": "observation.images.camera3"
+        }
+      }
+    },
+    {
+      "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": "tokenizer"
+      },
+      "artifacts": {
+        "tokenizer_name": "tokenizer"
+      }
+    },
+    {
+      "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": [
+              17
+            ]
+          }
+        },
+        "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 sha256:76228b12797e83b471eca7f1543770265c661f81752355a30f826976a6867d61
+size 9608

tokenizer/chat_template.jinja ADDED Viewed

	@@ -0,0 +1,2 @@


1	+ <\|im_start\|>{% for message in messages %}{{message['role'] \| capitalize}}{% if message['content'][0]['type'] == 'image' %}{{':'}}{% else %}{{': '}}{% endif %}{% for line in message['content'] %}{% if line['type'] == 'text' %}{{line['text']}}{% elif line['type'] == 'image' %}{{ '<image>' }}{% endif %}{% endfor %}<end_of_utterance>
2	+ {% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}

tokenizer/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,27 @@

+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "end_of_utterance_token": "<end_of_utterance>",
+  "eos_token": "<end_of_utterance>",
+  "fake_image_token": "<fake_token_around_image>",
+  "global_image_token": "<global-img>",
+  "image_token": "<image>",
+  "is_local": false,
+  "legacy": false,
+  "local_files_only": false,
+  "model_max_length": 8192,
+  "model_specific_special_tokens": {
+    "end_of_utterance_token": "<end_of_utterance>",
+    "fake_image_token": "<fake_token_around_image>",
+    "global_image_token": "<global-img>",
+    "image_token": "<image>"
+  },
+  "pad_token": "<|im_end|>",
+  "processor_class": "SmolVLMProcessor",
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "left",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

train_config.json ADDED Viewed

	@@ -0,0 +1,309 @@

+{
+    "dataset": {
+        "repo_id": "Suyang99/xlerobot-cup-grasp-20260820-0230",
+        "repo_type": "dataset",
+        "root": null,
+        "episodes": null,
+        "exclude_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",
+        "return_uint8": false,
+        "depth_output_unit": "mm",
+        "streaming": false,
+        "eval_split": 0.2
+    },
+    "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": [
+                    17
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": false,
+        "push_to_hub": false,
+        "repo_id": null,
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "lerobot/smolvla_base",
+        "pretrained_revision": null,
+        "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,
+        "compile_model": false,
+        "compile_mode": "max-autotune"
+    },
+    "reward_model": null,
+    "output_dir": "/home/robomates/Robotic_challenge/05-training/runs/smolvla_20260820-1502",
+    "job_name": "smolvla_cup_grasp_right",
+    "resume": false,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "num_workers": 2,
+    "batch_size": 2,
+    "prefetch_factor": 4,
+    "persistent_workers": true,
+    "dataloader_multiprocessing_context": "spawn",
+    "steps": 20000,
+    "env_eval_freq": 20000,
+    "log_freq": 100,
+    "eval_steps": 0,
+    "max_eval_samples": 0,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 2000,
+    "checkpoint_format": "safetensors",
+    "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
+    },
+    "parallelism": {
+        "dp_replicate": 1,
+        "dp_shard": 1,
+        "context_parallel": {
+            "ring_degree": 1,
+            "ulysses_degree": 1
+        },
+        "cfg_parallel": 1
+    },
+    "accelerator": {
+        "mixed_precision": "no",
+        "gradient_accumulation": {
+            "steps": 1
+        },
+        "fsdp": {
+            "reshard_after_forward": true,
+            "wrap_modules": null,
+            "min_num_params": null,
+            "cpu_offload": false,
+            "ignored_modules": null
+        },
+        "ddp": {
+            "find_unused_parameters": true,
+            "gradient_as_bucket_view": false,
+            "static_graph": false
+        },
+        "compile": {
+            "enabled": false,
+            "backend": "inductor",
+            "mode": null,
+            "regional": true
+        },
+        "activation_checkpointing": {
+            "mode": "none"
+        }
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 4,
+        "use_async_envs": true,
+        "recording": false,
+        "recording_repo_id": null,
+        "recording_private": false
+    },
+    "ema": {
+        "enable": false,
+        "decay": null,
+        "update_after_step": 0,
+        "inv_gamma": 1.0,
+        "power": 0.75,
+        "min_decay": 0.0,
+        "max_decay": 0.9999,
+        "use_for_eval": true
+    },
+    "wandb": {
+        "enable": false,
+        "disable_artifact": false,
+        "project": "lerobot",
+        "entity": null,
+        "notes": null,
+        "run_id": null,
+        "mode": null,
+        "add_tags": true
+    },
+    "peft": null,
+    "job": {
+        "target": null,
+        "image": "huggingface/lerobot-gpu:latest",
+        "timeout": "2d",
+        "detach": false,
+        "tags": []
+    },
+    "save_checkpoint_to_hub": false,
+    "sample_weighting": null,
+    "rename_map": {
+        "observation.images.head": "observation.images.camera1",
+        "observation.images.right_arm_wrist": "observation.images.camera2",
+        "observation.images.left_arm_wrist": "observation.images.camera3"
+    },
+    "checkpoint_path": null
+}