Commit
·
f6532e6
1
Parent(s):
652b9a5
Update README.md
Browse files
README.md
CHANGED
@@ -61,5 +61,12 @@ follow the above notebook by changing the model name to robert
|
|
61 |
}
|
62 |
```
|
63 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
64 |
## Reference:
|
65 |
* [Natural Language Processing with Transformer By Lewis Tunstall, Leandro von Werra, Thomas Wolf](https://learning.oreilly.com/library/view/natural-language-processing/9781098103231/)
|
|
|
61 |
}
|
62 |
```
|
63 |
|
64 |
+
## Model Performance Comparision on Emotion Dataset from Twitter:
|
65 |
+
|
66 |
+
| Model | Accuracy | F1 Score | Test Loss | Test Sample per Second |
|
67 |
+
| --- | --- | --- | --- | --- |
|
68 |
+
| Distilbert-base-uncased | 93.8 | 93.79 | 0.1472 | 398.69 |
|
69 |
+
| Roberta-base | 93.95 | 93.97 | 0.1437 | 195.639 |
|
70 |
+
|
71 |
## Reference:
|
72 |
* [Natural Language Processing with Transformer By Lewis Tunstall, Leandro von Werra, Thomas Wolf](https://learning.oreilly.com/library/view/natural-language-processing/9781098103231/)
|