add me-full epoch-30 checkpoint eval to model card

README.md

@@ -24,6 +24,7 @@ diversity (NJD), computed via `kin_flow.cli.bench` on 10 held-out test scenes wi
 | `se-panda_5000_170` | single-embodiment | Panda (2 DOF) | 170 / 500 | 97.8% | 0.293 | RTX 6000 Ada |
 | `se-shadow_5000_40` | single-embodiment | Shadow Hand (22 DOF) | 40 / 500 | 75.9% | 0.232 | RTX 6000 Ada |
 | `me-full_25000_5` | multi-embodiment | all 5 + z0 | 5 / 500 | 82.1% (mean) | 0.212 (mean) | MI300X (ROCm) |
+| `me-full_25000_30` | multi-embodiment | all 5 + z0 | 30 / 500 | 84.3% (mean) | 0.203 (mean) | MI300X (ROCm) |
 
 Single-embodiment models: `num_scenes=5000`. Multi-embodiment model: the paper's full
 configuration — `num_scenes=25000`, fp32, batch 5 scenes × 128 grasps, warmup-cosine LR
@@ -40,7 +41,18 @@ configuration — `num_scenes=25000`, fp32, batch 5 scenes × 128 grasps, warmup
 | Shadow Hand | 22 | 75.3% | 0.232 |
 | **mean** | | **82.1%** | **0.212** |
 
-Very early snapshot (epoch 5 of ~120 needed for convergence) — newer-epoch checkpoints
+### `me-full_25000_30` per-gripper eval (epoch 30)
+
+| Gripper | DOF | SR | NJD |
+|---|---|---|---|
+| Panda | 2 | 96.0% | 0.252 |
+| VX300 | 2 | 93.3% | 0.159 |
+| DexEE | 12 | 76.0% | 0.095 |
+| Allegro | 16 | 84.4% | 0.283 |
+| Shadow Hand | 22 | 71.6% | 0.224 |
+| **mean** | | **84.3%** | **0.203** |
+
+Still an early snapshot (epoch 30 of ~120 needed for convergence) — newer-epoch checkpoints
 will be added as training progresses.
 
 ## Loading
@@ -54,6 +66,7 @@ from kin_flow.net.kinematics_flow import KinematicsFlow, KinematicsFlowConfigura
 model = Trainer.get_model_from_checkpoint(model, "<path>/me-full_25000_5")
 ```
 
-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.
+Note: `me-full_25000_*` checkpoints were 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; they are not compatible with the original
+Param-of-list layout.