María Navas Loro
commited on
Commit
•
cccbbe8
1
Parent(s):
b314ae4
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# roberta-finetuned-CPV_Spanish
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne) on the
|
|
|
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.0465
|
| 21 |
- F1: 0.7918
|
|
@@ -24,18 +25,12 @@ It achieves the following results on the evaluation set:
|
|
| 24 |
- Coverage Error: 10.2744
|
| 25 |
- Label Ranking Average Precision Score: 0.7973
|
| 26 |
|
| 27 |
-
## Model description
|
| 28 |
-
|
| 29 |
-
More information needed
|
| 30 |
-
|
| 31 |
## Intended uses & limitations
|
| 32 |
|
| 33 |
-
|
| 34 |
|
| 35 |
## Training and evaluation data
|
| 36 |
|
| 37 |
-
More information needed
|
| 38 |
-
|
| 39 |
## Training procedure
|
| 40 |
|
| 41 |
### Training hyperparameters
|
|
|
|
| 15 |
|
| 16 |
# roberta-finetuned-CPV_Spanish
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [PlanTL-GOB-ES/roberta-base-bne](https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne) on a dataset derived from Spanish Public Procurement documents from 2019. The whole fine-tuning process is available in the following [Kaggle notebook](https://www.kaggle.com/code/marianavasloro/fine-tuned-roberta-for-spanish-cpv-codes).
|
| 19 |
+
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.0465
|
| 22 |
- F1: 0.7918
|
|
|
|
| 25 |
- Coverage Error: 10.2744
|
| 26 |
- Label Ranking Average Precision Score: 0.7973
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
## Intended uses & limitations
|
| 29 |
|
| 30 |
+
This model only predicts the first two digits of the CPV codes.
|
| 31 |
|
| 32 |
## Training and evaluation data
|
| 33 |
|
|
|
|
|
|
|
| 34 |
## Training procedure
|
| 35 |
|
| 36 |
### Training hyperparameters
|