Commit
•
ea6d424
1
Parent(s):
80a8a25
End of training
Browse files- README.md +10 -3
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Train Loss:
|
| 18 |
-
- Validation Loss: 2.
|
| 19 |
-
- Epoch:
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -43,6 +43,13 @@ The following hyperparameters were used during training:
|
|
| 43 |
| Train Loss | Validation Loss | Epoch |
|
| 44 |
|:----------:|:---------------:|:-----:|
|
| 45 |
| 3.2631 | 2.3702 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
|
| 48 |
### Framework versions
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Train Loss: 2.3123
|
| 18 |
+
- Validation Loss: 2.1399
|
| 19 |
+
- Epoch: 7
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 43 |
| Train Loss | Validation Loss | Epoch |
|
| 44 |
|:----------:|:---------------:|:-----:|
|
| 45 |
| 3.2631 | 2.3702 | 0 |
|
| 46 |
+
| 2.6166 | 2.2422 | 1 |
|
| 47 |
+
| 2.4974 | 2.2074 | 2 |
|
| 48 |
+
| 2.4288 | 2.1843 | 3 |
|
| 49 |
+
| 2.3837 | 2.1613 | 4 |
|
| 50 |
+
| 2.3503 | 2.1521 | 5 |
|
| 51 |
+
| 2.3263 | 2.1407 | 6 |
|
| 52 |
+
| 2.3123 | 2.1399 | 7 |
|
| 53 |
|
| 54 |
|
| 55 |
### Framework versions
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1201092992
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10e88ad5dc218432a135f55c98d33ae8116b479a5e6256b39f0acd2add491da9
|
| 3 |
size 1201092992
|