End of training
Browse files- README.md +8 -8
- pytorch_model.bin +1 -1
README.md
CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [ad019el/Kabyle_xlsr-finetuned-tamasheq.en](https://huggingface.co/ad019el/Kabyle_xlsr-finetuned-tamasheq.en) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 1.
|
20 |
-
- Wer: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
|
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
|
60 |
|
61 |
### Framework versions
|
62 |
|
63 |
-
- Transformers 4.
|
64 |
- Pytorch 2.0.1+cu118
|
65 |
- Datasets 2.14.4
|
66 |
- Tokenizers 0.13.3
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [ad019el/Kabyle_xlsr-finetuned-tamasheq.en](https://huggingface.co/ad019el/Kabyle_xlsr-finetuned-tamasheq.en) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.4417
|
20 |
+
- Wer: 0.8444
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
54 |
+
| 6.087 | 3.41 | 300 | 2.8648 | 1.0 |
|
55 |
+
| 2.3631 | 6.82 | 600 | 1.3254 | 0.8705 |
|
56 |
+
| 1.0058 | 10.23 | 900 | 1.3736 | 0.8829 |
|
57 |
+
| 0.7859 | 13.64 | 1200 | 1.3322 | 0.8733 |
|
58 |
+
| 0.6834 | 17.05 | 1500 | 1.4417 | 0.8444 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
62 |
|
63 |
+
- Transformers 4.33.0
|
64 |
- Pytorch 2.0.1+cu118
|
65 |
- Datasets 2.14.4
|
66 |
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262024813
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b126ad797b0635deb678753911532f0d4779b545d8b03f6b8b8a5aa01c82dbf
|
3 |
size 1262024813
|