Update MODEL_SUMMARY.txt - Run 20251104_133602

weights/David-partial_shared-cantor_scale/20251104_133602/MODEL_SUMMARY.txt

@@ -0,0 +1,58 @@
+
+╔══════════════════════════════════════════════════════════════╗
+║                      DAVID MODEL SUMMARY                      ║
+╠══════════════════════════════════════════════════════════════╣
+║                                                               ║
+║  🎯 VALIDATION ACCURACY: 81.28%                          ║
+║                                                               ║
+╚══════════════════════════════════════════════════════════════╝
+
+MODEL: David-partial_shared-cantor_scale
+RUN ID: 20251104_133602
+BEST EPOCH: 1/5
+
+═══════════════════════════════════════════════════════════════
+
+📊 PERFORMANCE BREAKDOWN
+
+Final Training Accuracy:  77.89%
+Best Validation Accuracy: 81.28%
+
+Per-Scale Accuracies:
+  • Scale  384: 80.39%
+  • Scale  768: 80.90%
+  • Scale 1024: 80.75%
+  • Scale 1280: 80.57%
+  • Scale 1536: 80.98%
+
+═══════════════════════════════════════════════════════════════
+
+🏗️  ARCHITECTURE
+
+Preset:        clip_vit_l14_cantor
+Sharing Mode:  partial_shared
+Fusion Mode:   cantor_scale
+Scales:        5 scales - [384, 768, 1024, 1280, 1536]
+Feature Dim:   768
+Parameters:    32,436,998
+
+═══════════════════════════════════════════════════════════════
+
+📈 TRAINING CURVE
+
+Epoch | Train Acc | Val Acc  | Learning Rate
+------|-----------|----------|--------------
+    1 |    77.89% |   81.28% 👑 | 9.76e-04
+
+═══════════════════════════════════════════════════════════════
+
+📁 FILES
+
+Best Model:    best_model_acc81.28.safetensors
+Config:        david_config.json
+Training Cfg:  train_config.json
+History:       training_history.json
+
+═══════════════════════════════════════════════════════════════
+
+Generated: 2025-11-04 13:40:59