restore original single-embodiment card; append me-full epoch-5 section

README.md

@@ -1,29 +1,38 @@
 ---
 license: agpl-3.0
 tags:
-- robotics
-- grasping
-- flow-matching
-- jax
-- flax
+  - grasping
+  - jax
+  - equivariance
+  - multi-embodiment
 ---
 
-# kinematics-flow — multi-embodiment grasp generation (early checkpoint)
+# Kinematics Flow checkpoints
 
-Checkpoint of the full multi-embodiment model from
-[Towards a Multi-Embodied Grasping Agent](https://arxiv.org/abs/2510.27420)
-(code: [boschresearch/kinematics-flow](https://github.com/boschresearch/kinematics-flow)),
-trained on AMD MI300X (ROCm) with the paper's full configuration:
-all five grippers (Panda, VX300, DexEE, Allegro, ShadowHand) + z0, 25,000 scenes,
-fp32, batch 5 scenes × 128 grasps, warmup-cosine LR (peak 3e-4).
+Single-embodiment checkpoints for [Kinematics Flow](https://github.com/boschresearch/kinematics-flow), from ["Towards a Multi-Embodied Grasping Agent"](https://arxiv.org/abs/2510.27420). These are **mid-training checkpoints**, not final converged models.
 
-## Contents
+## Checkpoints
 
-- `me-full_25000_5/` — Orbax (OCDBT) checkpoint at **epoch 5** (~25,000 train steps).
-  **Early checkpoint** — the paper trains ~120 epochs for full quality; this is a
-  work-in-progress snapshot, expect rough grasps.
+| Folder | Gripper | DOF | Epoch | Test success rate | Test NJD |
+|---|---|---|---|---|---|
+| `se-panda_5000_170` | Panda | 2 | 170 / 500 | 97.8% | 0.293 |
+| `se-shadow_5000_40` | Shadow Hand | 22 | 40 / 500 | 75.9% | 0.232 |
 
-## Loading
+Both trained with `num_scenes=5000` on a single RTX 6000 Ada (48GB). Eval numbers are simulation-based grasp success rate and normalized joint diversity (NJD), computed via `kin_flow.cli.bench` on 10 held-out test scenes (100 sampled grasps/scene each).
+
+Format: orbax/OCDBT checkpoint directories, loadable via `kin_flow.ctrl.trainer.Trainer.get_model_from_checkpoint`.
+
+## Multi-embodiment checkpoint
+
+- `me-full_25000_5/` — **epoch 5** (~25,000 train steps) of the paper's full
+  multi-embodiment configuration: all five grippers (Panda, VX300, DexEE, Allegro,
+  ShadowHand) + z0, `num_scenes=25000`, fp32, batch 5 scenes × 128 grasps,
+  warmup-cosine LR (peak 3e-4). Trained on a single AMD MI300X (ROCm).
+  **Very early snapshot** — the paper trains ~120 epochs for full quality; expect
+  rough grasps. Newer-epoch checkpoints will replace/join this one as training
+  progresses.
+
+### Loading
 
 ```python
 from kin_flow.ctrl.trainer import Trainer
@@ -32,6 +41,6 @@ from kin_flow.net.kinematics_flow import KinematicsFlow, KinematicsFlowConfigura
 model = Trainer.get_model_from_checkpoint(model, "<path>/me-full_25000_5")
 ```
 
-Note: trained with flax 0.11 and a per-path `nnx.Param` layout in
-`TPWithWeightsAndBiases` (`kin_flow/net/module/fctp.py`) — restore with a matching
-code state; checkpoints are not compatible with the original Param-of-list layout.
+Note: `me-full_25000_5` was trained with flax 0.11 using a per-path `nnx.Param`
+layout in `TPWithWeightsAndBiases` (`kin_flow/net/module/fctp.py`) — restore with a
+matching code state; it is not compatible with the original Param-of-list layout.