Training in progress epoch 4
Browse files
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 [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss: 7.
|
19 |
- Validation Loss: 2.5137
|
20 |
-
- Epoch:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -47,6 +47,7 @@ The following hyperparameters were used during training:
|
|
47 |
| 7.8734 | 2.6951 | 1 |
|
48 |
| 7.3007 | 2.5137 | 2 |
|
49 |
| 7.0408 | 2.5137 | 3 |
|
|
|
50 |
|
51 |
|
52 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 7.0270
|
19 |
- Validation Loss: 2.5137
|
20 |
+
- Epoch: 4
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
47 |
| 7.8734 | 2.6951 | 1 |
|
48 |
| 7.3007 | 2.5137 | 2 |
|
49 |
| 7.0408 | 2.5137 | 3 |
|
50 |
+
| 7.0270 | 2.5137 | 4 |
|
51 |
|
52 |
|
53 |
### Framework versions
|