Commit
•
1e87a72
1
Parent(s):
5962dcb
End of training
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 1.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -48,8 +48,8 @@ The following hyperparameters were used during training:
|
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
-
| No log | 1.0 | 250 | 1.
|
| 52 |
-
| 1.
|
| 53 |
|
| 54 |
|
| 55 |
### Framework versions
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 1.4090
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 48 |
|
| 49 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| No log | 1.0 | 250 | 1.4323 |
|
| 52 |
+
| 1.6994 | 2.0 | 500 | 1.4090 |
|
| 53 |
|
| 54 |
|
| 55 |
### Framework versions
|