jjmcarrascosa
commited on
Commit
•
37b4956
1
Parent(s):
aa1a4d1
Update README.md
Browse files
README.md
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
---
|
2 |
-
license: mit
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
- optuna
|
@@ -29,6 +28,10 @@ This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/
|
|
29 |
- a private one, provided by @Newtral, containing both tweets and news.
|
30 |
- one used for data augmentation purposes, containing only news, obtained from [SurgeHQ.ai](https://app.surgehq.ai/datasets/spanish-toxicity)
|
31 |
|
|
|
|
|
|
|
|
|
32 |
The test dataset was provided by @Newtral and was kept fixed.
|
33 |
|
34 |
It achieves the following results on the evaluation set:
|
@@ -41,18 +44,6 @@ It achieves the following results on the evaluation set:
|
|
41 |
- epoch: 5.0
|
42 |
- step: 3595
|
43 |
|
44 |
-
## Model description
|
45 |
-
|
46 |
-
More information needed
|
47 |
-
|
48 |
-
## Intended uses & limitations
|
49 |
-
|
50 |
-
More information needed
|
51 |
-
|
52 |
-
## Training and evaluation data
|
53 |
-
|
54 |
-
More information needed
|
55 |
-
|
56 |
## Training procedure
|
57 |
- Cleaning
|
58 |
- Data Augmentation
|
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
- optuna
|
|
|
28 |
- a private one, provided by @Newtral, containing both tweets and news.
|
29 |
- one used for data augmentation purposes, containing only news, obtained from [SurgeHQ.ai](https://app.surgehq.ai/datasets/spanish-toxicity)
|
30 |
|
31 |
+
**This model can not be used for commercial purposes**
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
The test dataset was provided by @Newtral and was kept fixed.
|
36 |
|
37 |
It achieves the following results on the evaluation set:
|
|
|
44 |
- epoch: 5.0
|
45 |
- step: 3595
|
46 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
47 |
## Training procedure
|
48 |
- Cleaning
|
49 |
- Data Augmentation
|