Commit
·
861ec86
1
Parent(s):
4f25031
Training in progress epoch 59
Browse files- README.md +4 -2
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -15,9 +15,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Train Loss: 0.
|
| 19 |
- Validation Loss: 2.2912
|
| 20 |
-
- Epoch:
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -101,6 +101,8 @@ The following hyperparameters were used during training:
|
|
| 101 |
| 0.5168 | 2.2444 | 55 |
|
| 102 |
| 0.5022 | 2.2660 | 56 |
|
| 103 |
| 0.4826 | 2.2912 | 57 |
|
|
|
|
|
|
|
| 104 |
|
| 105 |
|
| 106 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Train Loss: 0.4442
|
| 19 |
- Validation Loss: 2.2912
|
| 20 |
+
- Epoch: 59
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 101 |
| 0.5168 | 2.2444 | 55 |
|
| 102 |
| 0.5022 | 2.2660 | 56 |
|
| 103 |
| 0.4826 | 2.2912 | 57 |
|
| 104 |
+
| 0.4607 | 2.2922 | 58 |
|
| 105 |
+
| 0.4442 | 2.2912 | 59 |
|
| 106 |
|
| 107 |
|
| 108 |
### Framework versions
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 558172300
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d47eea9d24534fde96d10e7e9aadd1058e0692ed1547b0ea8ccf7a9442f7b2b6
|
| 3 |
size 558172300
|