update model card README.md
Browse files
README.md
CHANGED
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model was trained from scratch on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 2.
|
19 |
-
- Wer: 0.
|
20 |
-
- Cer: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -51,18 +51,19 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
54 |
-
| 1.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
|
|
61 |
|
62 |
|
63 |
### Framework versions
|
64 |
|
65 |
- Transformers 4.31.0
|
66 |
- Pytorch 2.0.1+cu117
|
67 |
-
- Datasets
|
68 |
- Tokenizers 0.13.3
|
|
|
15 |
|
16 |
This model was trained from scratch on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 2.5098
|
19 |
+
- Wer: 0.5366
|
20 |
+
- Cer: 0.2277
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
54 |
+
| 1.0449 | 3.49 | 400 | 1.7576 | 0.6270 | 0.2607 |
|
55 |
+
| 0.484 | 6.99 | 800 | 1.8072 | 0.6043 | 0.2536 |
|
56 |
+
| 0.3335 | 10.48 | 1200 | 2.0222 | 0.5892 | 0.2500 |
|
57 |
+
| 0.2559 | 13.97 | 1600 | 2.4174 | 0.5719 | 0.2448 |
|
58 |
+
| 0.1999 | 17.47 | 2000 | 2.2888 | 0.5566 | 0.2376 |
|
59 |
+
| 0.1546 | 20.96 | 2400 | 2.5271 | 0.5753 | 0.2400 |
|
60 |
+
| 0.1225 | 24.45 | 2800 | 2.4489 | 0.5427 | 0.2327 |
|
61 |
+
| 0.0983 | 27.95 | 3200 | 2.5098 | 0.5366 | 0.2277 |
|
62 |
|
63 |
|
64 |
### Framework versions
|
65 |
|
66 |
- Transformers 4.31.0
|
67 |
- Pytorch 2.0.1+cu117
|
68 |
+
- Datasets 2.14.4
|
69 |
- Tokenizers 0.13.3
|