laureanadcastro
commited on
Commit
•
9b773c4
1
Parent(s):
f398107
Training complete
Browse files- README.md +8 -12
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -18,25 +18,21 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss:
|
22 |
-
- Bleu:
|
23 |
-
- Gen Len:
|
24 |
|
25 |
## Model description
|
26 |
|
27 |
-
|
28 |
-
Utiliza la arquitectura seq2seq y está entrenado para traducir texto en español "normal" a español "inclusivo", donde se neutraliza el género gramatical para hacerlo más inclusivo.
|
29 |
|
30 |
## Intended uses & limitations
|
31 |
|
32 |
-
|
33 |
-
Es adecuado para aplicaciones que buscan promover la diversidad y la inclusión en el lenguaje escrito.
|
34 |
-
Sin embargo, es importante tener en cuenta que, aunque el modelo ha sido entrenado con datos específicos para la neutralización de género, puede haber casos donde la neutralización no sea perfecta o no se ajuste al contexto deseado.
|
35 |
|
36 |
## Training and evaluation data
|
37 |
|
38 |
-
|
39 |
-
Este conjunto de datos fue tokenizado utilizando el modelo "mbart-large-50". Durante el entrenamiento, se utilizó la métrica sacrebleu, ampliamente utilizada en el ámbito de la traducción automática, para evaluar el rendimiento del modelo.
|
40 |
|
41 |
## Training procedure
|
42 |
|
@@ -55,8 +51,8 @@ The following hyperparameters were used during training:
|
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
57 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
|
58 |
-
| No log | 1.0 |
|
59 |
-
|
|
60 |
|
61 |
|
62 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 5.2526
|
22 |
+
- Bleu: 20.3083
|
23 |
+
- Gen Len: 12.7561
|
24 |
|
25 |
## Model description
|
26 |
|
27 |
+
More information needed
|
|
|
28 |
|
29 |
## Intended uses & limitations
|
30 |
|
31 |
+
More information needed
|
|
|
|
|
32 |
|
33 |
## Training and evaluation data
|
34 |
|
35 |
+
More information needed
|
|
|
36 |
|
37 |
## Training procedure
|
38 |
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
|
54 |
+
| No log | 1.0 | 16 | 5.6569 | 18.8367 | 12.4878 |
|
55 |
+
| No log | 2.0 | 32 | 5.2526 | 20.3083 | 12.7561 |
|
56 |
|
57 |
|
58 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2444578688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9c1acdc7a336cb0a4c2d4926422c528569efc99c2405ca6b7279a5d167976fe
|
3 |
size 2444578688
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebf18d92d648889c5fb5c58fa774540de4761e8de498ad4c00dfad8e7be4b129
|
3 |
size 4856
|