Update README.md
Browse files
README.md
CHANGED
|
@@ -43,7 +43,10 @@ In this fine-tuning process, only the DoRA adapter components are trained. The o
|
|
| 43 |
The DoRA hyperparameters were selected to effectively balance adaptation capability and memory efficiency. The DoRA adapter achieved a significant improvement in performance, with the macro F1 score increasing from an initial value of **0.07** (before fine-tuning) to **0.50** (after fine-tuning).
|
| 44 |
|
| 45 |
Two confusion matrix heatmaps illustrate the performance change:
|
| 46 |
-
- **Heatmap Before Fine-Tuning:**
|
|
|
|
|
|
|
|
|
|
| 47 |
- **Heatmap After Fine-Tuning:**
|
| 48 |
|
| 49 |
|
|
|
|
| 43 |
The DoRA hyperparameters were selected to effectively balance adaptation capability and memory efficiency. The DoRA adapter achieved a significant improvement in performance, with the macro F1 score increasing from an initial value of **0.07** (before fine-tuning) to **0.50** (after fine-tuning).
|
| 44 |
|
| 45 |
Two confusion matrix heatmaps illustrate the performance change:
|
| 46 |
+
- **Heatmap Before Fine-Tuning:**
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
|
| 50 |
- **Heatmap After Fine-Tuning:**
|
| 51 |
|
| 52 |
|