e-hossam96
commited on
Commit
•
f0b017b
1
Parent(s):
3ddbc59
Update README.md
Browse files
README.md
CHANGED
@@ -13,8 +13,6 @@ language:
|
|
13 |
- ar
|
14 |
---
|
15 |
|
16 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
-
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
# arabic-nano-gpt
|
20 |
|
@@ -22,14 +20,6 @@ This model is a fine-tuned version of [openai-community/gpt2](https://huggingfac
|
|
22 |
It achieves the following results on the held-out test set:
|
23 |
- Loss: 3.28796
|
24 |
|
25 |
-
**Training Loss**
|
26 |
-
|
27 |
-
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ccee86374057a338e03c1e/970nr9bptjHSMsjLDHfaY.png)
|
28 |
-
|
29 |
-
**Validation Loss**
|
30 |
-
|
31 |
-
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ccee86374057a338e03c1e/GUbnak7yV02vd0NZhbeEO.png)
|
32 |
-
|
33 |
|
34 |
## Model description
|
35 |
|
@@ -61,7 +51,7 @@ The following hyperparameters were used during training:
|
|
61 |
|
62 |
### Training results
|
63 |
|
64 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
65 |
|:-------------:|:------:|:------:|:---------------:|
|
66 |
| 5.62 | 0.0585 | 1000 | 5.3754 |
|
67 |
| 4.6527 | 0.1170 | 2000 | 4.4918 |
|
@@ -214,7 +204,15 @@ The following hyperparameters were used during training:
|
|
214 |
| 3.4653 | 8.7149 | 149000 | 3.2857 |
|
215 |
| 3.4552 | 8.7733 | 150000 | 3.2861 |
|
216 |
| 3.47 | 8.8318 | 151000 | 3.2868 |
|
217 |
-
| 3.4627 | 8.8903 | 152000 | 3.2854 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
218 |
|
219 |
|
220 |
### Framework versions
|
|
|
13 |
- ar
|
14 |
---
|
15 |
|
|
|
|
|
16 |
|
17 |
# arabic-nano-gpt
|
18 |
|
|
|
20 |
It achieves the following results on the held-out test set:
|
21 |
- Loss: 3.28796
|
22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
+
<!-- | Training Loss | Epoch | Step | Validation Loss |
|
55 |
|:-------------:|:------:|:------:|:---------------:|
|
56 |
| 5.62 | 0.0585 | 1000 | 5.3754 |
|
57 |
| 4.6527 | 0.1170 | 2000 | 4.4918 |
|
|
|
204 |
| 3.4653 | 8.7149 | 149000 | 3.2857 |
|
205 |
| 3.4552 | 8.7733 | 150000 | 3.2861 |
|
206 |
| 3.47 | 8.8318 | 151000 | 3.2868 |
|
207 |
+
| 3.4627 | 8.8903 | 152000 | 3.2854 | -->
|
208 |
+
|
209 |
+
**Training Loss**
|
210 |
+
|
211 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ccee86374057a338e03c1e/970nr9bptjHSMsjLDHfaY.png)
|
212 |
+
|
213 |
+
**Validation Loss**
|
214 |
+
|
215 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ccee86374057a338e03c1e/GUbnak7yV02vd0NZhbeEO.png)
|
216 |
|
217 |
|
218 |
### Framework versions
|