Update README.md
Browse files
README.md
CHANGED
@@ -1,38 +1,32 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
|
4 |
-
|
5 |
-
|
|
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
-
|
9 |
-
-
|
10 |
-
|
|
|
11 |
---
|
12 |
|
13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
should probably proofread and complete it, then remove this comment. -->
|
15 |
|
16 |
-
#
|
|
|
|
|
|
|
17 |
|
18 |
-
This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the
|
19 |
It achieves the following results on the evaluation set:
|
20 |
- Loss: 0.1791
|
21 |
- Accuracy: 0.9461
|
22 |
|
23 |
-
##
|
24 |
-
|
25 |
-
More information needed
|
26 |
-
|
27 |
-
## Intended uses & limitations
|
28 |
-
|
29 |
-
More information needed
|
30 |
-
|
31 |
-
## Training and evaluation data
|
32 |
-
|
33 |
-
More information needed
|
34 |
-
|
35 |
-
## Training procedure
|
36 |
|
37 |
### Training hyperparameters
|
38 |
|
@@ -55,10 +49,6 @@ The following hyperparameters were used during training:
|
|
55 |
| 0.3122 | 0.19 | 1500 | 0.2578 | 0.9014 |
|
56 |
| 0.2975 | 0.25 | 2000 | 0.1992 | 0.9396 |
|
57 |
| 0.2877 | 0.31 | 2500 | 0.1791 | 0.9461 |
|
58 |
-
| 0.2797 | 0.38 | 3000 | 0.1953 | 0.9350 |
|
59 |
-
| 0.2714 | 0.44 | 3500 | 0.2240 | 0.9182 |
|
60 |
-
| 0.2678 | 0.5 | 4000 | 0.2097 | 0.9320 |
|
61 |
-
|
62 |
|
63 |
### Framework versions
|
64 |
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
datasets:
|
4 |
+
- LemeExploreNau/VeraCruz
|
5 |
+
language:
|
6 |
+
- pt
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
+
tags:
|
10 |
+
- Portuguese
|
11 |
+
- Brazilian
|
12 |
+
- Language Classification
|
13 |
---
|
14 |
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
+
# PeroVazPT-PTBR Classifier
|
19 |
+
|
20 |
+
## Model Description
|
21 |
+
The PeroVazPT-PTBR Classifier is designed to classify text between European Portuguese (PT-PT) and Brazilian Portuguese (PT-BR).
|
22 |
|
23 |
+
This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the [VeraCruz Dataset](https://huggingface.co/datasets/LemeExploreNau/VeraCruz).
|
24 |
It achieves the following results on the evaluation set:
|
25 |
- Loss: 0.1791
|
26 |
- Accuracy: 0.9461
|
27 |
|
28 |
+
## Training Data
|
29 |
+
The model was trained on the [VeraCruz Dataset](https://huggingface.co/datasets/LemeExploreNau/VeraCruz), a collection of text samples from both languages. The model was trained on a total of 500,000 examples, a evenly split between European Portuguese and Brazilian Portuguese, ensuring a balanced representation of both language variants.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
30 |
|
31 |
### Training hyperparameters
|
32 |
|
|
|
49 |
| 0.3122 | 0.19 | 1500 | 0.2578 | 0.9014 |
|
50 |
| 0.2975 | 0.25 | 2000 | 0.1992 | 0.9396 |
|
51 |
| 0.2877 | 0.31 | 2500 | 0.1791 | 0.9461 |
|
|
|
|
|
|
|
|
|
52 |
|
53 |
### Framework versions
|
54 |
|