Release DiscoDemo SFT

Browse files

Files changed (8) hide show

README.md +57 -0
config.json +87 -0
model.safetensors +3 -0
policy_postprocessor.json +32 -0
policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
policy_preprocessor.json +98 -0
policy_preprocessor_step_3_normalizer_processor.safetensors +3 -0
train_config.json +263 -0

README.md ADDED Viewed

	@@ -0,0 +1,57 @@

+---
+license: apache-2.0
+base_model: DAVIAN-Robotics/pi05_droid_jointpos
+pipeline_tag: robotics
+tags:
+- robotics
+- lerobot
+- pi05
+- imitation-learning
+- discodemo
+- franka
+---
+# DiscoDemo-Stage3_SFT-FMB_Round-alpha0
+A visuomotor **π0.5** policy for the **FMB-Round** task (insert a cylindrical peg into its hole on the FMB board), fine-tuned on demonstrations generated
+by the P-RFCL baseline generator (α = 0: the same reverse-curriculum RL without the diversity reward) of [DiscoDemo](https://davian-robotics.github.io/DiscoDemo/). It acts from camera images and joint states only,
+and transfers to the real Franka FR3 robot without real-world fine-tuning.
+| Stage | Repository |
+|---|---|
+| Generator (RL policy) | [`DAVIAN-Robotics/DiscoDemo-Stage1_RL-FMB_Round-alpha0`](https://huggingface.co/DAVIAN-Robotics/DiscoDemo-Stage1_RL-FMB_Round-alpha0) |
+| Generated dataset | [`DAVIAN-Robotics/DiscoDemo-Stage2_GenData-FMB_Round-alpha0`](https://huggingface.co/datasets/DAVIAN-Robotics/DiscoDemo-Stage2_GenData-FMB_Round-alpha0) |
+| Imitation policy (π0.5) | [`DAVIAN-Robotics/DiscoDemo-Stage3_SFT-FMB_Round-alpha0`](https://huggingface.co/DAVIAN-Robotics/DiscoDemo-Stage3_SFT-FMB_Round-alpha0) (this repository) |
+## Training
+| | |
+|---|---|
+| Base model | [`DAVIAN-Robotics/pi05_droid_jointpos`](https://huggingface.co/DAVIAN-Robotics/pi05_droid_jointpos) (π0.5 DROID, joint-position actions) |
+| Data | [`DAVIAN-Robotics/DiscoDemo-Stage2_GenData-FMB_Round-alpha0`](https://huggingface.co/datasets/DAVIAN-Robotics/DiscoDemo-Stage2_GenData-FMB_Round-alpha0) |
+| Steps | 20,000 |
+| Batch size | 16 |
+| Action chunk | 15 (relative to the current joint state) |
+| Cameras | over-the-shoulder and wrist |
+| Seed | 1000 |
+## Usage
+The policy is a [LeRobot](https://github.com/huggingface/lerobot) π0.5 checkpoint. Its pre- and post-processing
+pipeline uses DiscoDemo processing steps (relative actions, state tokenization), so loading it requires the DiscoDemo
+code: https://github.com/DAVIAN-Robotics/DiscoDemo.
+## License
+Apache-2.0, following the base model ([openpi](https://github.com/Physical-Intelligence/openpi)).
+## Citation
+```bibtex
+@article{park2026discodemo,
+  title   = {DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning},
+  author  = {Park, Minho and Kim, Kinam and Kim, Donghu and Lee, Byungkun and Hwang, Dongyoon and Shin, Yongjae and Hyung, Junha and Lee, Hojoon and Choo, Jaegul},
+  journal = {arXiv preprint},
+  year    = {2026}
+}
+```

config.json ADDED Viewed

	@@ -0,0 +1,87 @@

+{
+    "type": "pi05",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.images.base_0_rgb": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        },
+        "observation.images.left_wrist_0_rgb": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        },
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                8
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                8
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": false,
+    "push_to_hub": false,
+    "repo_id": null,
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": "sft/checkpoints/pi05-fr3-ins-round-v3-rs16-as0-press-a5l15-c1em6-s0-F1cm-3000-merged-delta-lr=2.5e-5-bs=16-steps=20000-chunk=15-s1000-pad1/checkpoints/last/pretrained_model",
+    "paligemma_variant": "gemma_2b",
+    "action_expert_variant": "gemma_300m",
+    "dtype": "bfloat16",
+    "chunk_size": 15,
+    "n_action_steps": 15,
+    "max_state_dim": 8,
+    "max_action_dim": 32,
+    "num_inference_steps": 10,
+    "time_sampling_beta_alpha": 1.5,
+    "time_sampling_beta_beta": 1.0,
+    "time_sampling_scale": 0.999,
+    "time_sampling_offset": 0.001,
+    "min_period": 0.004,
+    "max_period": 4.0,
+    "rtc_config": null,
+    "image_resolution": [
+        224,
+        224
+    ],
+    "empty_cameras": 0,
+    "tokenizer_max_length": 200,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "QUANTILES",
+        "ACTION": "QUANTILES"
+    },
+    "gradient_checkpointing": true,
+    "compile_model": false,
+    "compile_mode": "max-autotune",
+    "freeze_vision_encoder": false,
+    "train_expert_only": false,
+    "optimizer_lr": 2.5e-05,
+    "optimizer_betas": [
+        0.9,
+        0.95
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 0.01,
+    "optimizer_grad_clip_norm": 1.0,
+    "scheduler_warmup_steps": 1000,
+    "scheduler_decay_steps": 20000,
+    "scheduler_decay_lr": 2.5e-06
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:350b05f87262bd3e2773845875bce62ac05c675ca8bcd32f28afbdf2735618d1
+size 7473096344

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": [
+                            8
+                        ]
+                    }
+                },
+                "norm_map": {
+                    "VISUAL": "IDENTITY",
+                    "STATE": "QUANTILES",
+                    "ACTION": "QUANTILES"
+                }
+            },
+            "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 sha256:2f03fa0b9b667421d1ec3214f13fbca48311dcdd8533733635ce4d6231eb15d4
+size 5120

policy_preprocessor.json ADDED Viewed

	@@ -0,0 +1,98 @@

+{
+    "name": "policy_preprocessor",
+    "steps": [
+        {
+            "registry_name": "rename_observations_processor",
+            "config": {
+                "rename_map": {
+                    "observation.images.over_shoulder_left_camera": "observation.images.base_0_rgb",
+                    "observation.images.wrist_cam": "observation.images.left_wrist_0_rgb"
+                }
+            }
+        },
+        {
+            "registry_name": "to_batch_processor",
+            "config": {}
+        },
+        {
+            "registry_name": "action_delta_processor_step",
+            "config": {
+                "mask": [
+                    true,
+                    true,
+                    true,
+                    true,
+                    true,
+                    true,
+                    true,
+                    false
+                ],
+                "state_key": "observation.state"
+            }
+        },
+        {
+            "registry_name": "normalizer_processor",
+            "config": {
+                "eps": 1e-08,
+                "features": {
+                    "observation.images.base_0_rgb": {
+                        "type": "VISUAL",
+                        "shape": [
+                            3,
+                            480,
+                            640
+                        ]
+                    },
+                    "observation.images.left_wrist_0_rgb": {
+                        "type": "VISUAL",
+                        "shape": [
+                            3,
+                            480,
+                            640
+                        ]
+                    },
+                    "observation.state": {
+                        "type": "STATE",
+                        "shape": [
+                            8
+                        ]
+                    },
+                    "action": {
+                        "type": "ACTION",
+                        "shape": [
+                            8
+                        ]
+                    }
+                },
+                "norm_map": {
+                    "VISUAL": "IDENTITY",
+                    "STATE": "QUANTILES",
+                    "ACTION": "QUANTILES"
+                }
+            },
+            "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
+        },
+        {
+            "registry_name": "pi05_prepare_state_tokenizer_processor_step",
+            "config": {}
+        },
+        {
+            "registry_name": "tokenizer_processor",
+            "config": {
+                "max_length": 200,
+                "task_key": "task",
+                "padding_side": "right",
+                "padding": "max_length",
+                "truncation": true,
+                "tokenizer_name": "google/paligemma-3b-pt-224"
+            }
+        },
+        {
+            "registry_name": "device_processor",
+            "config": {
+                "device": "cuda",
+                "float_dtype": null
+            }
+        }
+    ]
+}

policy_preprocessor_step_3_normalizer_processor.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:6e48f472d365e0a461953444545224b929d6996475570d81371533d126339a6c
+size 5088

train_config.json ADDED Viewed

	@@ -0,0 +1,263 @@

+{
+    "dataset": {
+        "repo_id": "DAVIAN-Robotics/DiscoDemo-Stage2_GenData-FMB_Round-alpha0",
+        "root": null,
+        "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": "torchcodec",
+        "streaming": false
+    },
+    "env": null,
+    "policy": {
+        "type": "pi05",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.images.base_0_rgb": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            },
+            "observation.images.left_wrist_0_rgb": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            },
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    8
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    8
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": false,
+        "push_to_hub": false,
+        "repo_id": null,
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "sft/checkpoints/pi05-fr3-ins-round-v3-rs16-as0-press-a5l15-c1em6-s0-F1cm-3000-merged-delta-lr=2.5e-5-bs=16-steps=20000-chunk=15-s1000-pad1/checkpoints/last/pretrained_model",
+        "paligemma_variant": "gemma_2b",
+        "action_expert_variant": "gemma_300m",
+        "dtype": "bfloat16",
+        "chunk_size": 15,
+        "n_action_steps": 15,
+        "max_state_dim": 8,
+        "max_action_dim": 32,
+        "num_inference_steps": 10,
+        "time_sampling_beta_alpha": 1.5,
+        "time_sampling_beta_beta": 1.0,
+        "time_sampling_scale": 0.999,
+        "time_sampling_offset": 0.001,
+        "min_period": 0.004,
+        "max_period": 4.0,
+        "rtc_config": null,
+        "image_resolution": [
+            224,
+            224
+        ],
+        "empty_cameras": 0,
+        "tokenizer_max_length": 200,
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "QUANTILES",
+            "ACTION": "QUANTILES"
+        },
+        "gradient_checkpointing": true,
+        "compile_model": false,
+        "compile_mode": "max-autotune",
+        "freeze_vision_encoder": false,
+        "train_expert_only": false,
+        "optimizer_lr": 2.5e-05,
+        "optimizer_betas": [
+            0.9,
+            0.95
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 0.01,
+        "optimizer_grad_clip_norm": 1.0,
+        "scheduler_warmup_steps": 1000,
+        "scheduler_decay_steps": 20000,
+        "scheduler_decay_lr": 2.5e-06
+    },
+    "output_dir": null,
+    "job_name": "DiscoDemo-Stage3_SFT-FMB_Round-alpha0",
+    "resume": true,
+    "seed": 1000,
+    "num_workers": 8,
+    "batch_size": 16,
+    "steps": 20000,
+    "eval_freq": 0,
+    "log_freq": 100,
+    "tolerance_s": 0.01,
+    "save_checkpoint": true,
+    "save_freq": 1000,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 2.5e-05,
+        "weight_decay": 0.01,
+        "grad_clip_norm": 1.0,
+        "betas": [
+            0.9,
+            0.95
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "cosine_decay_with_warmup",
+        "num_warmup_steps": 1000,
+        "num_decay_steps": 20000,
+        "peak_lr": 2.5e-05,
+        "decay_lr": 2.5e-06
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 50,
+        "use_async_envs": false
+    },
+    "wandb": {
+        "enable": false,
+        "disable_artifact": true,
+        "project": null,
+        "entity": null,
+        "notes": null,
+        "run_id": null,
+        "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.over_shoulder_left_camera": "observation.images.base_0_rgb",
+        "observation.images.wrist_cam": "observation.images.left_wrist_0_rgb"
+    },
+    "checkpoint_path": "sft/checkpoints/pi05-fr3-ins-round-v3-rs16-as0-press-a5l15-c1em6-s0-F1cm-3000-merged-delta-lr=2.5e-5-bs=16-steps=20000-chunk=15-s1000-pad1/checkpoints/last",
+    "tune_targets": [
+        "visual",
+        "llm",
+        "action_expert"
+    ],
+    "num_save_checkpoints": 3,
+    "gradient_accumulation_steps": 1,
+    "robolab_eval": true,
+    "robolab_eval_freq": 5000,
+    "robolab_eval_num_envs": 50,
+    "robolab_eval_noise_cm": 30,
+    "robolab_eval_init_pose": "pregrasp:0.03,15",
+    "robolab_eval_init_pose_source": "onthefly",
+    "robolab_eval_init_pose_split": "train",
+    "robolab_eval_render_res": 270,
+    "robolab_eval_task": "libs/real2sim/real2sim/tasks/fr3_peg_insert_round.py",
+    "robolab_eval_gripper": "panda",
+    "robolab_eval_port": 28333,
+    "robolab_eval_max_episode_steps": 0,
+    "robolab_eval_robot_variant": "fr3",
+    "robolab_eval_sysid_workcell": "libs/real2sim/assets/workcell.json",
+    "robolab_eval_canonical_env_version": "fr3-peg-insert-round-v3",
+    "robolab_eval_control_decimation": 6,
+    "robolab_eval_collision_config_yaml": null,
+    "robolab_eval_success_hold_steps": 20,
+    "disable_proprioceptive_obs": false,
+    "policy_cameras": null,
+    "pad_state_first": false,
+    "action_delta": true,
+    "action_delta_mask": [
+        7,
+        -1
+    ],
+    "include_velocity": false,
+    "skill_z": false,
+    "debug": false,
+    "disable_robocasa_conditioning": true
+}