Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -27,12 +27,38 @@
|
|
27 |
|
28 |
## Performance Metrics
|
29 |
|
30 |
-
- Training Time: 1.
|
31 |
- Training MSE: 0.739313
|
32 |
- Testing MSE: 0.762029
|
33 |
- Training R²: 0.003906
|
34 |
- Testing R²: -0.044366
|
35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
## Usage
|
37 |
|
38 |
```python
|
|
|
27 |
|
28 |
## Performance Metrics
|
29 |
|
30 |
+
- Training Time: 1.55 seconds
|
31 |
- Training MSE: 0.739313
|
32 |
- Testing MSE: 0.762029
|
33 |
- Training R²: 0.003906
|
34 |
- Testing R²: -0.044366
|
35 |
|
36 |
+
## Model Analysis
|
37 |
+
|
38 |
+
### Predictions vs True Values
|
39 |
+
![Predictions](./plots/predictions.png)
|
40 |
+
|
41 |
+
This plot shows how well the model's predictions match the true values:
|
42 |
+
- Points on the red line indicate perfect predictions
|
43 |
+
- Spread around the line shows prediction uncertainty
|
44 |
+
- Systematic deviations indicate bias
|
45 |
+
|
46 |
+
### Error Distribution
|
47 |
+
![Error Distribution](./plots/error_distribution.png)
|
48 |
+
|
49 |
+
This plot shows the distribution of prediction errors:
|
50 |
+
- Centered around zero indicates unbiased predictions
|
51 |
+
- Width shows prediction precision
|
52 |
+
- Shape reveals error patterns
|
53 |
+
|
54 |
+
### Dimension-wise Performance
|
55 |
+
![Dimension MSE](./plots/dimension_mse.png)
|
56 |
+
|
57 |
+
This plot shows the MSE for each embedding dimension:
|
58 |
+
- Lower bars indicate better predictions
|
59 |
+
- Variations show which dimensions are harder to predict
|
60 |
+
- Can guide targeted improvements
|
61 |
+
|
62 |
## Usage
|
63 |
|
64 |
```python
|