Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,30 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
library_name: transformers
|
| 6 |
+
tags:
|
| 7 |
+
- medical
|
| 8 |
+
- healthcare
|
| 9 |
+
- clinical
|
| 10 |
+
- perioperative care
|
| 11 |
+
base_model: microsoft/deberta-v3-large
|
| 12 |
+
inference: false
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
# Training Dataset
|
| 18 |
+
|
| 19 |
+
This was trained on the [UtkMl's Twitter Spam Detection dataset](https://www.kaggle.com/c/twitter-spam/overview).
|
| 20 |
+
|
| 21 |
+
# Metrics
|
| 22 |
+
|
| 23 |
+
Based on a 80-10-10 train-val-test split, the following results were obtained on the test set:
|
| 24 |
+
- Accuracy: 0.9779
|
| 25 |
+
- Precision: 0.9781
|
| 26 |
+
- Recall: 0.9779
|
| 27 |
+
- F1-Score: 0.9779
|
| 28 |
+
|
| 29 |
+
## Questions?
|
| 30 |
+
contact me at alba@wustl.edu
|