Update README.md

README.md

@@ -19,21 +19,18 @@ model-index:
       name: rating_dr2
       type: dataset
     metrics:
-    - name: log-based ordinal loss with distance power 3.0
-      type: loss
-      value: 0.004970851354300976
     - name: off by 1 accuracy
       type: accuracy
-      value: 100.00
+      value: 74.78991596638656
     - name: mean squared error for ordinal data
       type: mse
-      value: 0.000
+      value: 0.773109243697479
     - name: weighted F1 score
       type: f1
-      value: 1.000
+      value: 0.76386248572931
     - name: Kendall's tau coefficient
       type: Kendall's tau
-      value: 1.000
+      value: 0.8081294201575603
     source:
       name: Keling Wang
       url: https://github.com/Keling-Wang
@@ -59,12 +56,12 @@ This model predicts strength of causation (SoC) labels based on the text inputs
 # Performance and hyperparameters
 ## Test metrics
 This model achieves the following results on the test dataset. The test dataset is a 25% held-out stratified split of the entire dataset with `SEED=114514`.
- * Loss: 0.0049709
- * Off-by-1 accuracy: 100.0000
- * Off-by-2 accuracy: 100.0000
- * MSE for ordinal data: 0.0000
- * Weighted F1: 1.0000
- * Kendall's Tau: 1.0000
+ * Loss: 18.2347
+ * Off-by-1 accuracy: 74.7899
+ * Off-by-2 accuracy: 91.5966
+ * MSE for ordinal data: 0.7731
+ * Weighted F1: 0.7639
+ * Kendall's Tau: 0.8081
 
 ## Hyperparameter tuning metrics
 This model achieves the following averaged results during 4-fold cross-validation with best hyperparameters in hyperparameter tuning process: