update model card README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# distilbert-base-uncased-finetuned-squad
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -41,9 +43,18 @@ The following hyperparameters were used during training:
|
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
- num_epochs: 3
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
### Framework versions
|
| 45 |
|
| 46 |
-
- Transformers 4.
|
| 47 |
- Pytorch 1.13.1+cu116
|
| 48 |
-
- Datasets 2.
|
| 49 |
- Tokenizers 0.13.2
|
|
|
|
| 15 |
# distilbert-base-uncased-finetuned-squad
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.1562
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
- num_epochs: 3
|
| 45 |
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 50 |
+
| 1.2299 | 1.0 | 5533 | 1.1785 |
|
| 51 |
+
| 0.9671 | 2.0 | 11066 | 1.1274 |
|
| 52 |
+
| 0.76 | 3.0 | 16599 | 1.1562 |
|
| 53 |
+
|
| 54 |
+
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
+
- Transformers 4.27.0
|
| 58 |
- Pytorch 1.13.1+cu116
|
| 59 |
+
- Datasets 2.10.1
|
| 60 |
- Tokenizers 0.13.2
|