NorahAlshahrani
commited on
Commit
•
17fa035
1
Parent(s):
1550f57
Update README.md
Browse files
README.md
CHANGED
@@ -21,8 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
21 |
|
22 |
# Adv_BERT_Hard
|
23 |
|
24 |
-
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv2](https://huggingface.co/aubmindlab/bert-base-arabertv2) on Hotel Arabic Reviews Dataset (HARD) dataset besides our adversarial examples.
|
25 |
-
It achieves the following results on the evaluation set:
|
26 |
- Loss: 0.4285
|
27 |
- Accuracy: 0.8267
|
28 |
|
@@ -43,7 +42,7 @@ It achieves the following results on the evaluation set:
|
|
43 |
```
|
44 |
|
45 |
## Training procedure
|
46 |
-
We have trained this model using the
|
47 |
|
48 |
### Training hyperparameters
|
49 |
|
|
|
21 |
|
22 |
# Adv_BERT_Hard
|
23 |
|
24 |
+
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv2](https://huggingface.co/aubmindlab/bert-base-arabertv2) on the Hotel Arabic Reviews Dataset (HARD) dataset besides our generated adversarial examples. It achieves the following results on the evaluation set:
|
|
|
25 |
- Loss: 0.4285
|
26 |
- Accuracy: 0.8267
|
27 |
|
|
|
42 |
```
|
43 |
|
44 |
## Training procedure
|
45 |
+
We have trained this model using the PaperSpace GPU-Cloud service. We used a machine with 8 CPUs, 45GB RAM, and A6000 GPU with 48GB RAM.
|
46 |
|
47 |
### Training hyperparameters
|
48 |
|