Update MODEL_SUMMARY.txt - Run 20251104_122236

weights/David-partial_shared-geometric_attention/20251104_122236/MODEL_SUMMARY.txt

@@ -3,26 +3,26 @@
 ║                      DAVID MODEL SUMMARY                      ║
 ╠══════════════════════════════════════════════════════════════╣
 ║                                                               ║
-║  🎯 VALIDATION ACCURACY: 77.02%                          ║
+║  🎯 VALIDATION ACCURACY: 77.60%                          ║
 ║                                                               ║
 ╚══════════════════════════════════════════════════════════════╝
 
 MODEL: David-partial_shared-geometric_attention
 RUN ID: 20251104_122236
-BEST EPOCH: 2/5
+BEST EPOCH: 3/5
 
 ═══════════════════════════════════════════════════════════════
 
 📊 PERFORMANCE BREAKDOWN
 
-Final Training Accuracy:  79.74%
-Best Validation Accuracy: 77.02%
+Final Training Accuracy:  81.77%
+Best Validation Accuracy: 77.60%
 
 Per-Scale Accuracies:
-  • Scale  256: 75.45%
-  • Scale  512: 76.35%
-  • Scale  768: 76.49%
-  • Scale 1024: 76.65%
+  • Scale  256: 76.05%
+  • Scale  512: 77.07%
+  • Scale  768: 77.01%
+  • Scale 1024: 77.12%
 
 ═══════════════════════════════════════════════════════════════
 
@@ -42,17 +42,18 @@ Parameters:    12,599,556
 Epoch | Train Acc | Val Acc  | Learning Rate
 ------|-----------|----------|--------------
     1 |    71.75% |   76.11% | 9.76e-04
-    2 |    79.74% |   77.02% 👑 | 9.05e-04
+    2 |    79.74% |   77.02% | 9.05e-04
+    3 |    81.77% |   77.60% 👑 | 7.94e-04
 
 ═══════════════════════════════════════════════════════════════
 
 📁 FILES
 
-Best Model:    best_model_acc77.02.safetensors
+Best Model:    best_model_acc77.60.safetensors
 Config:        david_config.json
 Training Cfg:  train_config.json
 History:       training_history.json
 
 ═══════════════════════════════════════════════════════════════
 
-Generated: 2025-11-04 12:26:25
+Generated: 2025-11-04 12:28:19