Commit
•
dbfafa6
1
Parent(s):
90e63b5
update model card README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 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.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -47,14 +47,14 @@ The following hyperparameters were used during training:
|
|
| 47 |
|
| 48 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
-
| No log | 1.0 | 250 | 2.
|
| 51 |
-
| 2.
|
| 52 |
-
| 2.
|
| 53 |
|
| 54 |
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
-
- Transformers 4.
|
| 58 |
-
- Pytorch 2.0.1+
|
| 59 |
- Datasets 2.12.0
|
| 60 |
- Tokenizers 0.13.3
|
|
|
|
| 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: 1.6589
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 47 |
|
| 48 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| No log | 1.0 | 250 | 2.3366 |
|
| 51 |
+
| 2.8308 | 2.0 | 500 | 1.7977 |
|
| 52 |
+
| 2.8308 | 3.0 | 750 | 1.6589 |
|
| 53 |
|
| 54 |
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
+
- Transformers 4.29.2
|
| 58 |
+
- Pytorch 2.0.1+cpu
|
| 59 |
- Datasets 2.12.0
|
| 60 |
- Tokenizers 0.13.3
|