model: graph_conv-relation_attention_h128_l3_edge_prediction | (graph_conv-relation_attention_h128_l3) | WandB: hh8kfhbv

README.md

@@ -39,7 +39,7 @@ optionally incorporating relation types for relation-aware prediction.
   - Type: `relation_attention`
   - Relation-Aware: ✓
 
-**Training Date**: 2025-12-25
+**Training Date**: 2025-12-30
 
 For detailed experiment and training settings see this repository's `config.json` file.
 
@@ -47,15 +47,15 @@ For detailed experiment and training settings see this repository's `config.json
 
 | Metric | Value |
 |--------|-------|
-| Validation AUC | 0.7844 |
-| Test AUC | 0.7878 |
-| Validation AP | 0.7801 |
-| Test AP | 0.7849 |
+| Validation relation-weighted AUC | 0.8432 |
+| Validation AUC | 0.7983 |
+| Validation AP | 0.7972 |
+| Best Epoch | 1499.0000 |
 
 
 ## Links
 
-- 📊 [W&B Run](https://wandb.ai/napistu/napistu-experiments/runs/zn6x58le)
+- 📊 [W&B Run](https://wandb.ai/napistu/napistu-experiments/runs/hh8kfhbv)
 - 🌐 [Napistu](https://napistu.com)
 - 💻 [GitHub Repository](https://github.com/napistu/Napistu-Torch)
 - 📖 [Read the Docs](https://napistu-torch.readthedocs.io/en/latest)
@@ -71,7 +71,7 @@ To reproduce the environment used for training, run the following commands:
 pip install torch==2.8.0
 pip install torch-scatter torch-sparse -f https://data.pyg.org/whl/2.8.0+cpu.html
 pip install 'napistu==0.8.5'
-pip install 'napistu-torch[pyg,lightning]==0.3.2'
+pip install 'napistu-torch[pyg,lightning]==0.3.4'
 ```
 
 ### 2. Setup Data Store