Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
This model is a fine-tuned version of [MMG/bert-base-spanish-wwm-cased-finetuned-sqac](https://huggingface.co/MMG/bert-base-spanish-wwm-cased-finetuned-sqac) on the squad_es dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 1.5325
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -40,15 +42,10 @@ The following hyperparameters were used during training:
|
|
| 40 |
- seed: 42
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
-
- num_epochs:
|
| 44 |
|
| 45 |
### Training results
|
| 46 |
|
| 47 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
-
|:-------------:|:-----:|:-----:|:---------------:|
|
| 49 |
-
| 1.4496 | 1.0 | 11134 | 1.5325 |
|
| 50 |
-
|
| 51 |
-
|
| 52 |
### Framework versions
|
| 53 |
|
| 54 |
- Transformers 4.13.0
|
|
|
|
| 16 |
This model is a fine-tuned version of [MMG/bert-base-spanish-wwm-cased-finetuned-sqac](https://huggingface.co/MMG/bert-base-spanish-wwm-cased-finetuned-sqac) on the squad_es dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
- Loss: 1.5325
|
| 19 |
+
- {'exact_match': 60.30274361400189, 'f1': 77.01962587890856}
|
| 20 |
+
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 42 |
- seed: 42
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 3
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
- Transformers 4.13.0
|