Update model card metrics

README.md

@@ -45,11 +45,11 @@ A diagram becomes its Gauss sequence: walk the knot and, at each crossing, recor
 
 | | |
 |---|---|
-| Parameters | 4,924,943 (6 layers, width 256) |
-| Steps | 20000, 512 knots (two diagrams each) per step |
-| Learning rate | 0.0003, cosine; temperature 0.05 |
-| Final loss | 0.6226 (contrastive 0.1426) |
-| Hardware | NVIDIA A10G, 102 min |
+| Parameters | 4,974,095 (6 layers, width 256) |
+| Steps | 10000, 512 knots (two diagrams each) per step |
+| Learning rate | 0.0001, cosine; temperature 0.05 |
+| Final loss | 1.1689 (contrastive 0.5045) |
+| Hardware | NVIDIA A10G, 92 min |
 
 ## 📊 Results
 
@@ -57,8 +57,8 @@ Each test diagram is a fresh scramble. The model names it by the nearest canonic
 
 | Knots | n | Top-1 | Top-5 | Signature | Determinant ±10% | Volume MAE |
 |---|---|---|---|---|---|---|
-| seen | 46676 | 0.881 | 0.976 | 0.917 | 0.267 | 1.237 |
-| unseen | 5184 | 0.88 | 0.976 | 0.891 | 0.248 | 1.39 |
+| seen | 46676 | 0.874 | 0.978 | 0.926 | 0.264 | 1.21 |
+| unseen | 5184 | 0.867 | 0.976 | 0.896 | 0.246 | 1.373 |
 
 Chance top-1 is 7.7e-05. For an exact answer, use SnapPy's `identify()`.