Update README.md
Browse files
README.md
CHANGED
|
@@ -24,16 +24,16 @@ model-index:
|
|
| 24 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 25 |
should probably proofread and complete it, then remove this comment. -->
|
| 26 |
|
| 27 |
-
#
|
|
|
|
|
|
|
| 28 |
|
| 29 |
-
This model is a fine-tuned version of [bart-turkish](https://huggingface.co/bart-turkish) on the mlsum tu dataset.
|
| 30 |
It achieves the following results on the evaluation set:
|
| 31 |
-
|
| 32 |
- Rouge1: 43.2049
|
| 33 |
- Rouge2: 30.7082
|
| 34 |
- Rougel: 38.1981
|
| 35 |
- Rougelsum: 39.9453
|
| 36 |
-
- Gen Len: 34.5978
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
@@ -87,7 +87,6 @@ The following hyperparameters were used during training:
|
|
| 87 |
| 2.3605 | 14.0 | 54530 | 3.5306 | 34.9545 | 24.4365 | 31.6208 | 32.4711 | 19.9366 |
|
| 88 |
| 2.3216 | 15.0 | 58425 | 3.5379 | 34.9079 | 24.4077 | 31.5734 | 32.4287 | 19.9365 |
|
| 89 |
|
| 90 |
-
|
| 91 |
### Framework versions
|
| 92 |
|
| 93 |
- Transformers 4.11.3
|
|
|
|
| 24 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 25 |
should probably proofread and complete it, then remove this comment. -->
|
| 26 |
|
| 27 |
+
# mukayese/bart-turkish-mlsum
|
| 28 |
+
|
| 29 |
+
This model is a initialized from scratch and trained only the mlsum/tu dataset with no pre-training.
|
| 30 |
|
|
|
|
| 31 |
It achieves the following results on the evaluation set:
|
| 32 |
+
|
| 33 |
- Rouge1: 43.2049
|
| 34 |
- Rouge2: 30.7082
|
| 35 |
- Rougel: 38.1981
|
| 36 |
- Rougelsum: 39.9453
|
|
|
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 87 |
| 2.3605 | 14.0 | 54530 | 3.5306 | 34.9545 | 24.4365 | 31.6208 | 32.4711 | 19.9366 |
|
| 88 |
| 2.3216 | 15.0 | 58425 | 3.5379 | 34.9079 | 24.4077 | 31.5734 | 32.4287 | 19.9365 |
|
| 89 |
|
|
|
|
| 90 |
### Framework versions
|
| 91 |
|
| 92 |
- Transformers 4.11.3
|