README: add me-full_25000_120 (final epoch-120 model, eval pending)

README.md

@@ -26,6 +26,7 @@ diversity (NJD), computed via `kin_flow.cli.bench` on 10 held-out test scenes wi
 | `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) |
 | `me-full_25000_90` | multi-embodiment | all 5 + z0 | 90 / 500 | 86.4% (mean) | 0.212 (mean) | MI300X (ROCm) |
+| `me-full_25000_120` | multi-embodiment | all 5 + z0 | **120** (target) | eval pending | eval pending | 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
@@ -66,8 +67,13 @@ step; epoch numbers here are the corrected true dataset-pass count.
 | Shadow Hand | 22 | 79.2% | 0.243 |
 | **mean** | | **86.4%** | **0.212** |
 
-Approaching convergence (epoch 90 of ~120 needed, per the original repo's own README
-guidance) — newer-epoch checkpoints will be added as training progresses.
+### `me-full_25000_120` — final model (epoch 120, training complete)
+
+Training finished 2026-07-15 at exactly **120.0 true dataset passes** (gradient step
+302,000 = 3,000,000 scene-visits / 25,000 scenes), the convergence point recommended by
+the original repo's README. Saved from the step-302,000 train-state checkpoint, so it
+also contains optimizer state for further fine-tuning. Per-gripper eval is pending and
+will be added here once complete.
 
 ## Loading