Model save
Browse files- README.md +11 -6
- model.safetensors +1 -1
README.md
CHANGED
@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [riotu-lab/ArabianGPT-01B](https://huggingface.co/riotu-lab/ArabianGPT-01B) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss:
|
22 |
-
- Bleu: 0.
|
23 |
-
- Rouge1: 0.
|
24 |
-
- Rouge2: 0.
|
25 |
-
- Rougel: 0.
|
26 |
|
27 |
## Model description
|
28 |
|
@@ -48,10 +48,15 @@ The following hyperparameters were used during training:
|
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
- lr_scheduler_warmup_steps: 500
|
51 |
-
- num_epochs:
|
52 |
|
53 |
### Training results
|
54 |
|
|
|
|
|
|
|
|
|
|
|
55 |
|
56 |
|
57 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [riotu-lab/ArabianGPT-01B](https://huggingface.co/riotu-lab/ArabianGPT-01B) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 2.6229
|
22 |
+
- Bleu: 0.1607
|
23 |
+
- Rouge1: 0.4264
|
24 |
+
- Rouge2: 0.1631
|
25 |
+
- Rougel: 0.3675
|
26 |
|
27 |
## Model description
|
28 |
|
|
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
- lr_scheduler_warmup_steps: 500
|
51 |
+
- num_epochs: 5.0
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Rouge1 | Rouge2 | Rougel |
|
56 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|:------:|
|
57 |
+
| 3.359 | 1.5674 | 500 | 3.1283 | 0.1142 | 0.3298 | 0.0843 | 0.2561 |
|
58 |
+
| 2.9208 | 3.1348 | 1000 | 2.7298 | 0.1491 | 0.4041 | 0.1430 | 0.3408 |
|
59 |
+
| 2.619 | 4.7022 | 1500 | 2.6229 | 0.1607 | 0.4264 | 0.1631 | 0.3675 |
|
60 |
|
61 |
|
62 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 539218560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bc210fd300ba6db0ea195ede5aa1e5c7469b4c97ae2abd88f2fbed47317d68d
|
3 |
size 539218560
|