Update README - Run 20251104_133602

README.md

@@ -21,7 +21,7 @@ model-index:
       type: imagenet-1k
     metrics:
     - type: accuracy
-      value: 81.28
+      value: 82.41
 ---
 
 # David: Multi-Scale Feature Classifier
@@ -51,16 +51,16 @@ as class prototypes with role-weighted similarity computation (Rose Loss).
 ## Performance
 
 ### Best Results
-- **Validation Accuracy**: 81.28%
-- **Best Epoch**: 0
-- **Final Train Accuracy**: 77.89%
+- **Validation Accuracy**: 82.41%
+- **Best Epoch**: 1
+- **Final Train Accuracy**: 85.08%
 
 ### Per-Scale Performance
-- **Scale 384**: 80.39%
-- **Scale 768**: 80.90%
-- **Scale 1024**: 80.75%
-- **Scale 1280**: 80.57%
-- **Scale 1536**: 80.98%
+- **Scale 384**: 81.66%
+- **Scale 768**: 81.83%
+- **Scale 1024**: 81.73%
+- **Scale 1280**: 82.14%
+- **Scale 1536**: 81.93%
 
 
 ## Usage
@@ -81,8 +81,8 @@ AbstractPhil/gated-david/
 │       └── 20251104_133602/
 │           ├── MODEL_SUMMARY.txt     # 🎯 Human-readable performance summary
 │           ├── training_history.json # 📈 Epoch-by-epoch training curve
-│           ├── best_model_acc81.28.safetensors  # ⭐ Accuracy in filename!
-│           ├── best_model_acc81.28_metadata.json
+│           ├── best_model_acc82.41.safetensors  # ⭐ Accuracy in filename!
+│           ├── best_model_acc82.41_metadata.json
 │           ├── final_model.safetensors
 │           ├── checkpoint_epoch_X_accYY.YY.safetensors
 │           ├── david_config.json
@@ -104,7 +104,7 @@ from huggingface_hub import hf_hub_download
 # Specify model variant and run
 model_name = "david_clip_vit_l14_cantor"
 run_id = "20251104_133602"
-accuracy = "81.28"  # From MODELS_INDEX.json
+accuracy = "82.41"  # From MODELS_INDEX.json
 
 # Download config
 config_path = hf_hub_download(
@@ -210,4 +210,4 @@ Special thanks to Claude (Anthropic) for debugging assistance.
 
 ---
 
-*Generated on 2025-11-04 13:41:01*
+*Generated on 2025-11-04 13:43:45*