Update README.md
Browse files
README.md
CHANGED
|
@@ -18,9 +18,17 @@ It achieves the following results on the evaluation set:
|
|
| 18 |
- Loss: 0.1218
|
| 19 |
- Accuracy: 0.9451
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
## Model description
|
| 22 |
|
| 23 |
-
|
| 24 |
|
| 25 |
## Intended uses & limitations
|
| 26 |
|
|
|
|
| 18 |
- Loss: 0.1218
|
| 19 |
- Accuracy: 0.9451
|
| 20 |
|
| 21 |
+
# Latest finetune 5 Dec 2023
|
| 22 |
+
{'eval_loss': 0.12179878354072571,
|
| 23 |
+
'eval_accuracy': 0.9450980392156862,
|
| 24 |
+
'eval_runtime': 5.8053,
|
| 25 |
+
'eval_samples_per_second': 43.925,
|
| 26 |
+
'eval_steps_per_second': 2.756,
|
| 27 |
+
'epoch': 20.0}
|
| 28 |
+
|
| 29 |
## Model description
|
| 30 |
|
| 31 |
+
Finetuned distilbert-uncased on prompts that are either malicious or benign.
|
| 32 |
|
| 33 |
## Intended uses & limitations
|
| 34 |
|