Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
Using combined dataset from multiple sources for safe vs unsafe text classification.
|
| 2 |
+
|
| 3 |
+
This is an initial experiment with results below:
|
| 4 |
+
|
| 5 |
+
```
|
| 6 |
+
{'test_loss': 0.0818108394742012,
|
| 7 |
+
'test_accuracy': 0.9797578509269769,
|
| 8 |
+
'test_f1': 0.9796642969399756,
|
| 9 |
+
'test_recall': 0.9901676829268292,
|
| 10 |
+
'test_precision': 0.9854357885155124,
|
| 11 |
+
'test_runtime': 75.8752,
|
| 12 |
+
'test_samples_per_second': 209.001,
|
| 13 |
+
'test_steps_per_second': 13.074}
|
| 14 |
+
```
|
| 15 |
+
|
| 16 |
+
142k samples for train, 15k for test.
|
| 17 |
+
|
| 18 |
+
---
|
| 19 |
+
metrics:
|
| 20 |
+
- accuracy
|
| 21 |
+
- recall
|
| 22 |
+
- precision
|
| 23 |
+
- f1
|
| 24 |
+
pipeline_tag: text-classification
|
| 25 |
+
---
|