Upload README.md with huggingface_hub

README.md

@@ -19,20 +19,23 @@ model-index:
       type: topic-drift-detection
       name: Topic Drift Detection
     dataset:
-      name: leonvanbokhorst/topic-drift
+      name: leonvanbokhorst/topic-drift-v2
       type: conversations
     metrics:
       - name: Test RMSE
         type: rmse
-        value: 0.0129
+        value: 0.0153
       - name: Test R²
         type: r2
-        value: 0.8373
+        value: 0.8500
+      - name: Test Loss 
+        type: loss
+        value: 0.0002
 ---
 
 # Topic Drift Detector Model
 
-## Version: v20241225_090654
+## Version: v20241225_160448
 
 This model detects topic drift in conversations using an enhanced attention-based architecture. Trained on the [leonvanbokhorst/topic-drift](https://huggingface.co/datasets/leonvanbokhorst/topic-drift) dataset.
 
@@ -47,18 +50,18 @@ This model detects topic drift in conversations using an enhanced attention-base
 ## Performance Metrics
 ```txt
 === Full Training Results ===
-Best Validation RMSE: 0.0107
-Best Validation R²: 0.8867
+Best Validation RMSE: 0.0145
+Best Validation R²: 0.8656
 
 === Test Set Results ===
 Loss: 0.0002
-RMSE: 0.0129
-R²: 0.8373
+RMSE: 0.0153
+R²: 0.8500
 
 ```
 
 ## Training Curves
-![Training Curves](plots/v20241225_090654/training_curves.png)
+![Training Curves](plots/v20241225_160448/training_curves.png)
 
 ## Usage
 ```python
@@ -70,7 +73,7 @@ base_model = AutoModel.from_pretrained('BAAI/bge-m3')
 tokenizer = AutoTokenizer.from_pretrained('BAAI/bge-m3')
 
 # Load topic drift detector
-model = torch.load('models/v20241225_090654/topic_drift_model.pt')
+model = torch.load('models/v20241225_160448/topic_drift_model.pt')
 model.eval()
 
 # Prepare conversation window (8 turns)