Upload policy weights, train config and readme

README.md

@@ -0,0 +1,70 @@
+---
+datasets: TynClause/cvit-task-clean-table-100E-RJ
+library_name: lerobot
+license: apache-2.0
+model_name: pi05
+pipeline_tag: robotics
+tags:
+- robotics
+- lerobot
+- pi05
+---
+
+# Model Card for pi05
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+**π₀.₅ (Pi05) Policy**
+
+π₀.₅ is a Vision-Language-Action model with open-world generalization, from Physical Intelligence. The LeRobot implementation is adapted from their open source OpenPI repository.
+
+**Model Overview**
+
+π₀.₅ represents a significant evolution from π₀, developed by Physical Intelligence to address a big challenge in robotics: open-world generalization. While robots can perform impressive tasks in controlled environments, π₀.₅ is designed to generalize to entirely new environments and situations that were never seen during training.
+
+For more details, see the [Physical Intelligence π₀.₅ blog post](https://www.physicalintelligence.company/blog/pi05).
+
+
+This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
+See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
+
+---
+
+## How to Get Started with the Model
+
+For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).
+Below is the short version on how to train and run inference/eval:
+
+### Train from scratch
+
+```bash
+lerobot-train \
+  --dataset.repo_id=${HF_USER}/<dataset> \
+  --policy.type=act \
+  --output_dir=outputs/train/<desired_policy_repo_id> \
+  --job_name=lerobot_training \
+  --policy.device=cuda \
+  --policy.repo_id=${HF_USER}/<desired_policy_repo_id>
+  --wandb.enable=true
+```
+
+_Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
+
+### Evaluate the policy/run inference
+
+```bash
+lerobot-record \
+  --robot.type=so100_follower \
+  --dataset.repo_id=<hf_user>/eval_<dataset> \
+  --policy.path=<hf_user>/<desired_policy_repo_id> \
+  --episodes=10
+```
+
+Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.
+
+---
+
+## Model Details
+
+- **License:** apache-2.0

config.json

@@ -0,0 +1,99 @@
+{
+    "type": "pi05",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                6
+            ]
+        },
+        "observation.images.front": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        },
+        "observation.images.wrist": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                6
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": false,
+    "push_to_hub": true,
+    "repo_id": "TynClause/pi05-clean-table",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": "outputs/pi05_training/checkpoints/015000/pretrained_model",
+    "paligemma_variant": "gemma_2b",
+    "action_expert_variant": "gemma_300m",
+    "dtype": "bfloat16",
+    "chunk_size": 50,
+    "n_action_steps": 50,
+    "max_state_dim": 32,
+    "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,
+    "use_relative_actions": true,
+    "relative_exclude_joints": [
+        "gripper"
+    ],
+    "action_feature_names": [
+        "shoulder_pan.pos",
+        "shoulder_lift.pos",
+        "elbow_flex.pos",
+        "wrist_flex.pos",
+        "wrist_roll.pos",
+        "gripper.pos"
+    ],
+    "rtc_config": null,
+    "image_resolution": [
+        224,
+        224
+    ],
+    "empty_cameras": 0,
+    "tokenizer_max_length": 200,
+    "normalization_mapping": {
+        "ACTION": "MEAN_STD",
+        "STATE": "MEAN_STD",
+        "VISUAL": "IDENTITY"
+    },
+    "gradient_checkpointing": true,
+    "compile_model": true,
+    "compile_mode": "max-autotune",
+    "freeze_vision_encoder": false,
+    "train_expert_only": true,
+    "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": 30000,
+    "scheduler_decay_lr": 2.5e-06
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9859980d25e804cd00dabc16b08707af2519a5eb539dbede8ced8c4b22aeced0
+size 9354050752

train_config.json

@@ -0,0 +1,237 @@
+{
+    "dataset": {
+        "repo_id": "TynClause/cvit-task-clean-table-100E-RJ",
+        "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",
+        "return_uint8": false,
+        "streaming": false
+    },
+    "env": null,
+    "policy": {
+        "type": "pi05",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    6
+                ]
+            },
+            "observation.images.front": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            },
+            "observation.images.wrist": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    6
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": false,
+        "push_to_hub": true,
+        "repo_id": "TynClause/pi05-clean-table",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "outputs/pi05_training/checkpoints/015000/pretrained_model",
+        "paligemma_variant": "gemma_2b",
+        "action_expert_variant": "gemma_300m",
+        "dtype": "bfloat16",
+        "chunk_size": 50,
+        "n_action_steps": 50,
+        "max_state_dim": 32,
+        "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,
+        "use_relative_actions": true,
+        "relative_exclude_joints": [
+            "gripper"
+        ],
+        "action_feature_names": [
+            "shoulder_pan.pos",
+            "shoulder_lift.pos",
+            "elbow_flex.pos",
+            "wrist_flex.pos",
+            "wrist_roll.pos",
+            "gripper.pos"
+        ],
+        "rtc_config": null,
+        "image_resolution": [
+            224,
+            224
+        ],
+        "empty_cameras": 0,
+        "tokenizer_max_length": 200,
+        "normalization_mapping": {
+            "ACTION": "MEAN_STD",
+            "STATE": "MEAN_STD",
+            "VISUAL": "IDENTITY"
+        },
+        "gradient_checkpointing": true,
+        "compile_model": true,
+        "compile_mode": "max-autotune",
+        "freeze_vision_encoder": false,
+        "train_expert_only": true,
+        "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": 30000,
+        "scheduler_decay_lr": 2.5e-06
+    },
+    "reward_model": null,
+    "output_dir": "outputs/pi05_training",
+    "job_name": "pi05_training",
+    "resume": true,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "num_workers": 4,
+    "batch_size": 16,
+    "prefetch_factor": 4,
+    "persistent_workers": true,
+    "steps": 20000,
+    "eval_freq": 20000,
+    "log_freq": 200,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 5000,
+    "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": 30000,
+        "peak_lr": 2.5e-05,
+        "decay_lr": 2.5e-06
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 19,
+        "use_async_envs": true
+    },
+    "wandb": {
+        "enable": true,
+        "disable_artifact": false,
+        "project": "lerobot",
+        "entity": null,
+        "notes": null,
+        "run_id": "0osbw9ui",
+        "mode": null,
+        "add_tags": true
+    },
+    "peft": null,
+    "sample_weighting": null,
+    "rename_map": {},
+    "checkpoint_path": "outputs/pi05_training/checkpoints/015000"
+}