Update README.md

README.md

@@ -60,12 +60,13 @@ The classifier was trained on 500,000 pairs of code files and their scores from
 We added a classification head with a single regression output to StarEncoder and trained the model for 20 epochs with a learning rate of 3e-4. During training, the embedding and encoder layers were frozen to focus on the classification head. 
 
 It achieves the following results on the evaluation set:
-- Loss: 0.3771
-- Precision: 0.4052
-- Recall: 0.2706
-- F1 Macro: 0.2936
-- Accuracy: 0.5963
-- F1 Binary Minimum3: 0.5462
+- Loss: 0.3403
+- Precision: 0.6596
+- Recall: 0.3962
+- F1 Macro: 0.4436
+- Accuracy: 0.6112
+- F1 Binary Minimum3: 0.7282
+- F1 Binary Minimum2: 0.9673
 
 While the macro F1 scores across the 1-5 rating scale are relatively low due to the model's difficulty in distinguishing between higher-rated samples, the classifier performs well for our primary filtering task. When converting to binary classification, using a threshold of 2 achieves the F1 scores ranges between 0.8 and 0.9 for most Stack-Edu  classifiers, whereas a threshold of 3 yields F1 scores between 0.5 and 0.8. With the Highest being Python, SQL, C, Rust and the lowest being TypeScript and PHP.