Update README.md

README.md

@@ -25,6 +25,23 @@ So this essentially means the model accumulated knowledge of 4,320,000,000,000 s
 
 Additionally, it retained knowledge of enough to retain an accuracy score above zero and even produce cohesive head results accurate enough to say that it can see a piece of the whole.
 
+
+## 🔬 Training Details
+
+- **Optimizer**: AdamW (lr=1e-3, weight_decay=0.001)
+- **Batch Size**: 16
+- **Data**: Symbolic prompt synthesis (complexity 1-5)
+- **Feature Extraction**: SD1.5 UNet blocks (spatial, not pooled)
+- **Pool Mode**: Mean spatial pooling
+
+## 📈 Training Metrics
+
+Final metrics from epoch 40:
+- Cayley Loss: 0.1018
+- Timestep Accuracy: 39.08%
+- Pattern Accuracy: 44.25%
+- Full Accuracy: 26.57%
+
 ## 🎯 Model Overview
 
 GeoDavidCollective Enhanced is a sophisticated multi-expert geometric classification system that learns from Stable Diffusion 1.5's internal representations. Using ProjectiveHead architecture with Cayley-Menger geometry, it achieves efficient pattern recognition across timestep and semantic spaces.
@@ -99,22 +116,6 @@ with torch.no_grad():
 ```
 
 
-## 🔬 Training Details
-
-- **Optimizer**: AdamW (lr=1e-3, weight_decay=0.001)
-- **Batch Size**: 16
-- **Data**: Symbolic prompt synthesis (complexity 1-5)
-- **Feature Extraction**: SD1.5 UNet blocks (spatial, not pooled)
-- **Pool Mode**: Mean spatial pooling
-
-## 📈 Training Metrics
-
-Final metrics from epoch 40:
-- Cayley Loss: 0.1018
-- Timestep Accuracy: 39.08%
-- Pattern Accuracy: 44.25%
-- Full Accuracy: 26.57%
-
 ## 🎓 Research Context
 
 This model is part of the geometric deep learning research exploring: