Update README.md

README.md

@@ -89,7 +89,7 @@ print("Vulnerable Code" if predicted_label == 1 else "Safe Code")
 ### Training Data
 - **Dataset:** `DetectVul/devign`
 - **Classes:** `0 (Safe)`, `1 (Vulnerable)`
-- **Size:** 50,000+ code snippets
+- **Size:** 17483 code snippets
 
 ### Training Procedure
 - **Optimizer:** AdamW
@@ -102,7 +102,7 @@ print("Vulnerable Code" if predicted_label == 1 else "Safe Code")
 
 ### Training Metrics
 | Metric  | Score |
-|---------|--------|
+|------------|-------------|
 | **Train Loss** | 0.4835 |
 | **Evaluation Loss** | 0.6855 |
 | **Accuracy** | 68.34% |
@@ -125,6 +125,6 @@ The model was evaluated using **20% of the dataset**, with the following results
 ## Environmental Impact
 
 | Factor  | Value |
-|---------|--------|
+|-----------|----------|
 | **GPU Used** | 2x T4 GPU |
 | **Training Time** | ~1 hour |