End of training
Browse files
README.md
CHANGED
|
@@ -13,7 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# bart-with-vocab-noise-data
|
| 15 |
|
| 16 |
-
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -43,6 +45,11 @@ The following hyperparameters were used during training:
|
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
|
| 48 |
### Framework versions
|
|
|
|
| 13 |
|
| 14 |
# bart-with-vocab-noise-data
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.1180
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 45 |
|
| 46 |
### Training results
|
| 47 |
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 50 |
+
| 0.1538 | 0.87 | 500 | 0.1459 |
|
| 51 |
+
| 0.098 | 1.73 | 1000 | 0.1252 |
|
| 52 |
+
| 0.0738 | 2.6 | 1500 | 0.1180 |
|
| 53 |
|
| 54 |
|
| 55 |
### Framework versions
|