pakawadeep
commited on
Commit
•
d26a940
1
Parent(s):
2eba4f2
Training in progress epoch 14
Browse files- README.md +5 -4
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -16,11 +16,11 @@ probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Train Loss: 5.
|
20 |
-
- Validation Loss: 4.
|
21 |
-
- Train Bleu: 0.
|
22 |
- Train Gen Len: 127.0
|
23 |
-
- Epoch:
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -60,6 +60,7 @@ The following hyperparameters were used during training:
|
|
60 |
| 5.9571 | 4.9619 | 0.0003 | 127.0 | 11 |
|
61 |
| 5.7344 | 4.8588 | 0.0 | 7.0 | 12 |
|
62 |
| 5.5347 | 4.7700 | 0.0 | 127.0 | 13 |
|
|
|
63 |
|
64 |
|
65 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Train Loss: 5.4059
|
20 |
+
- Validation Loss: 4.7055
|
21 |
+
- Train Bleu: 0.0005
|
22 |
- Train Gen Len: 127.0
|
23 |
+
- Epoch: 14
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
60 |
| 5.9571 | 4.9619 | 0.0003 | 127.0 | 11 |
|
61 |
| 5.7344 | 4.8588 | 0.0 | 7.0 | 12 |
|
62 |
| 5.5347 | 4.7700 | 0.0 | 127.0 | 13 |
|
63 |
+
| 5.4059 | 4.7055 | 0.0005 | 127.0 | 14 |
|
64 |
|
65 |
|
66 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2225556280
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b12081175657a084ca3f3fd78e4b71829a9c193e171f1e9f30b4e653a9ad6bf
|
3 |
size 2225556280
|