Upload policy weights, train config and readme

README.md

@@ -1,204 +1,168 @@
 ---
-library_name: peft
+base_model: lerobot/pi05_base
+datasets: fruits_orange
+library_name: lerobot
+license: apache-2.0
+model_name: pi05
+pipeline_tag: robotics
 tags:
-- base_model:adapter:/data/wanshan/workspace/VLA/lerobot/checkpoints/lerobot--pi05-base
-- lora
+- robotics
+- pi05
+- lerobot
 ---
 
-# Model Card for Model ID
+# Model Card for pi05
 
 <!-- Provide a quick summary of what the model is/does. -->
 
 
+[π₀.₅ (Pi05)](https://www.physicalintelligence.company/blog/pi05) is a Vision-Language-Action model from Physical Intelligence designed for open-world generalization: it evolves π₀ to generalize to entirely new environments and situations that were never seen during training. The LeRobot implementation is adapted from their open-source OpenPI repository.
 
-## Model Details
-
-### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
 
 
+<!-- A short demo is worth more than any description! Record a GIF/video of the policy
+running on your robot, upload it to this repo, and embed it here:
+<p align="center">
+  <img src="https://huggingface.co/<hf_user>/<policy_repo_id>/resolve/main/demo.gif" width="60%"/>
+</p>
+-->
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
 
-### Model Sources [optional]
+Learn how to train and run it in the [LeRobot pi05 guide](https://huggingface.co/docs/lerobot/main/en/pi05), or browse the [full documentation](https://huggingface.co/docs/lerobot/index).
 
-<!-- Provide the basic links for the model. -->
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+---
 
-## Uses
+## Model Details
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+- **License:** apache-2.0
+- **Fine-tuned from:** [lerobot/pi05_base](https://huggingface.co/lerobot/pi05_base)
+- **Robot type:** `piper_follower`
+- **Cameras:** `r_wrist`, `top`, `realsense`
 
-### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+## Inputs & Outputs
 
-[More Information Needed]
+The policy consumes these observation features and produces these action features.
 
-### Downstream Use [optional]
+**Inputs**
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+| Feature | Type | Shape |
+| --- | --- | --- |
+| `observation.state` | STATE | `(7,)` |
+| `observation.images.r_wrist` | VISUAL | `(3, 640, 480)` |
+| `observation.images.top` | VISUAL | `(3, 480, 640)` |
+| `observation.images.realsense` | VISUAL | `(3, 480, 640)` |
 
-[More Information Needed]
+**Outputs**
 
-### Out-of-Scope Use
+| Feature | Type | Shape |
+| --- | --- | --- |
+| `action` | ACTION | `(7,)` |
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
 
-[More Information Needed]
+## Training Dataset
 
-## Bias, Risks, and Limitations
+- **Repository:** [fruits_orange](https://huggingface.co/datasets/fruits_orange)
+- **Episodes:** 110
+- **Frames:** 57380
+- **Frame rate:** 30 FPS
+- **Task(s):** "Pick up the orange into the plate.", "Pick up the lemon into the plate.", "Pick up the kiwifruit into the plate."
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+<a class="flex" href="https://huggingface.co/spaces/lerobot/visualize_dataset?path=fruits_orange">
+<img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/visualize-this-dataset-xl.svg"/>
+<img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/visualize-this-dataset-xl-dark.svg"/>
+</a>
 
-[More Information Needed]
 
-### Recommendations
+## Training Configuration
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+| Setting | Value |
+| --- | --- |
+| Training steps | 20000 |
+| Batch size | 10 |
+| Optimizer | adamw |
+| Learning rate | 2.5e-05 |
+| Seed | 1000 |
+| LeRobot version | 0.6.1 |
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+---
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
+New to LeRobot? These guides cover the full workflow:
 
-### Training Data
+- **[Install LeRobot](https://huggingface.co/docs/lerobot/main/en/installation)** �� set up the `lerobot` package.
+- **[Hardware setup](https://huggingface.co/docs/lerobot/main/en/hardware_guide)** — assemble, wire, and calibrate your robot and cameras.
+- **[Record data & train a policy](https://huggingface.co/docs/lerobot/en/il_robots)** — the end-to-end imitation-learning walkthrough.
+- **[CLI cheat-sheet](https://huggingface.co/docs/lerobot/main/en/cheat-sheet)** — quick reference for the `lerobot-*` commands.
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+The short version to run and train this policy:
 
-[More Information Needed]
+### Run the policy on your robot
 
-### Training Procedure
+```bash
+lerobot-rollout \
+  --strategy.type=base \
+  --robot.type=piper_follower \
+  --robot.port=<your_robot_port> \
+  --robot.cameras="{ <camera_1>: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}, <camera_2>: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}}" \
+  --policy.path=samithva/pi05_fruits_orange \
+  --task="Pick up the orange into the plate." \
+  --duration=60
+```
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+Replace the remaining `<...>` placeholders with your own values: `--robot.port` and the camera names/indices are specific to your machine, and the camera names must match the observation keys this policy was trained on.
 
-#### Preprocessing [optional]
+When `--strategy.type=base` is used the script doesn't record the episodes. Skipping duration will make the policy run indefinitely. For more information look at [rollout documentation](https://huggingface.co/docs/lerobot/main/en/inference).
 
-[More Information Needed]
+### Train your own policy
 
+This policy type is usually fine-tuned from the pretrained base model [lerobot/pi05_base](https://huggingface.co/lerobot/pi05_base):
 
-#### Training Hyperparameters
+```bash
+lerobot-train \
+  --dataset.repo_id=${HF_USER}/<dataset> \
+  --policy.path=lerobot/pi05_base \
+  --output_dir=outputs/train/<policy_repo_id> \
+  --job_name=lerobot_training \
+  --policy.device=cuda \
+  --policy.repo_id=${HF_USER}/<policy_repo_id> \
+  --wandb.enable=true
+```
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+_Writes checkpoints to `outputs/train/<policy_repo_id>/checkpoints/`._
 
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
+---
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
+<!-- Report real-robot results here: run the policy several times per task and count the
+successes. Delete the "No evaluation results" line and fill in this table instead:
 
-<!-- Relevant interpretability work for the model goes here -->
+| Task | Trials | Successes | Success rate |
+| ---- | ------ | --------- | ------------ |
+| pick the lego brick | 10 | 8 | 80% |
 
-[More Information Needed]
+Also worth noting: anything that affects difficulty (new object positions, lighting,
+distractors, a different robot of the same type, ...).
+-->
 
-## Environmental Impact
+_No evaluation results have been provided for this policy yet._
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
+---
 
-## Model Card Contact
+## Citation
 
-[More Information Needed]
-### Framework versions
+If you use this policy, please cite the method linked in the description above, along with LeRobot:
 
-- PEFT 0.20.0
+```bibtex
+@misc{cadene2024lerobot,
+    author = {Cadene, Remi and Alibert, Simon and Soare, Alexander and Gallouedec, Quentin and Zouitine, Adil and Palma, Steven and Kooijmans, Pepijn and Aractingi, Michel and Shukor, Mustafa and Aubakirova, Dana and Russi, Martino and Capuano, Francesco and Pascal, Caroline and Choghari, Jade and Moss, Jess and Wolf, Thomas},
+    title = {LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch},
+    howpublished = "\url{https://github.com/huggingface/lerobot}",
+    year = {2024}
+}
+```

adapter_config.json

@@ -19,7 +19,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 128,
   "lora_bias": false,
   "lora_dropout": 0.0,
   "lora_ga_config": null,
@@ -30,7 +30,7 @@
   "peft_type": "LORA",
   "peft_version": "0.20.0",
   "qalora_group_size": 16,
-  "r": 16,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": "(.*\\.gemma_expert\\..*\\.self_attn\\.(q|v)_proj|model\\.(state_proj|action_in_proj|action_out_proj|action_time_mlp_in|action_time_mlp_out))",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f00b16a85e089d7b25de74f5f59b88a0bad849b144d4a626c1544fc435b2b1c1
-size 5161624
+oid sha256:f2d767c17e7fedb01fca58ed004192c4288b2add4df1cf88f320a3cb399e3fad
+size 20607744

config.json

@@ -91,7 +91,7 @@
         "ACTION": "QUANTILES"
     },
     "gradient_checkpointing": false,
-    "compile_model": true,
+    "compile_model": false,
     "compile_mode": "max-autotune",
     "freeze_vision_encoder": false,
     "train_expert_only": false,

train_config.json

@@ -1,8 +1,8 @@
 {
     "dataset": {
-        "repo_id": "sigs-eilab/fruits_orange",
+        "repo_id": "fruits_orange",
         "repo_type": "dataset",
-        "root": "datasets/fruits_orange",
+        "root": "./datasets/fruits_orange",
         "episodes": null,
         "image_transforms": {
             "enable": false,
@@ -177,7 +177,7 @@
             "ACTION": "QUANTILES"
         },
         "gradient_checkpointing": false,
-        "compile_model": true,
+        "compile_model": false,
         "compile_mode": "max-autotune",
         "freeze_vision_encoder": false,
         "train_expert_only": false,
@@ -199,8 +199,8 @@
     "resume": false,
     "seed": 1000,
     "cudnn_deterministic": false,
-    "num_workers": 8,
-    "batch_size": 8,
+    "num_workers": 5,
+    "batch_size": 10,
     "prefetch_factor": 4,
     "persistent_workers": true,
     "dataloader_multiprocessing_context": "spawn",
@@ -245,7 +245,7 @@
         "project": "lerobot",
         "entity": null,
         "notes": null,
-        "run_id": "jcys2pi0",
+        "run_id": "5oephurk",
         "mode": null,
         "add_tags": true
     },
@@ -254,8 +254,8 @@
         "full_training_modules": null,
         "method_type": "LORA",
         "init_type": null,
-        "r": 16,
-        "lora_alpha": 32
+        "r": 64,
+        "lora_alpha": 128
     },
     "job": {
         "target": null,