Update README.md
Browse files
README.md
CHANGED
|
@@ -43,6 +43,18 @@ This model converts natural language questions into SQL queries by leveraging th
|
|
| 43 |
|
| 44 |
## Performance
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
**Overall Performance Summary**
|
| 47 |
|
| 48 |
The model achieved a **39.17% execution accuracy** on the Spider development set, correctly generating 405 out of 1,034 SQL queries. While this represents moderate performance, it demonstrates the model's capability to handle basic to intermediate SQL generation tasks across diverse database domains.
|
|
|
|
| 43 |
|
| 44 |
## Performance
|
| 45 |
|
| 46 |
+
### Performance Comparison
|
| 47 |
+
|
| 48 |
+
| Metric | Base Qwen Model | Fine-tuned Model |
|
| 49 |
+
|--------|----------------|------------------|
|
| 50 |
+
| **Total Queries** | 1,034 | 1,034 |
|
| 51 |
+
| **Execution Success** | 570 | 577 |
|
| 52 |
+
| **Execution Success Rate** | 55.1% | 55.8% |
|
| 53 |
+
| **Correct Results** | 357 | 405 |
|
| 54 |
+
| **Execution Accuracy** | 34.5% | 39.2% |
|
| 55 |
+
| **Parse Errors** | 464 | 457 |
|
| 56 |
+
| **Evaluation Time** | 84.9 min | 38.7 min |
|
| 57 |
+
|
| 58 |
**Overall Performance Summary**
|
| 59 |
|
| 60 |
The model achieved a **39.17% execution accuracy** on the Spider development set, correctly generating 405 out of 1,034 SQL queries. While this represents moderate performance, it demonstrates the model's capability to handle basic to intermediate SQL generation tasks across diverse database domains.
|