Hermann-Meier
commited on
Upload TFBertForPreTraining
Browse files- README.md +11 -3
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -15,7 +15,7 @@ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown
|
|
15 |
It achieves the following results on the evaluation set:
|
16 |
- Train Loss: nan
|
17 |
- Validation Loss: nan
|
18 |
-
- Epoch:
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -41,8 +41,16 @@ The following hyperparameters were used during training:
|
|
41 |
|
42 |
| Train Loss | Validation Loss | Epoch |
|
43 |
|:----------:|:---------------:|:-----:|
|
44 |
-
|
|
45 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
|
|
15 |
It achieves the following results on the evaluation set:
|
16 |
- Train Loss: nan
|
17 |
- Validation Loss: nan
|
18 |
+
- Epoch: 9
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
41 |
|
42 |
| Train Loss | Validation Loss | Epoch |
|
43 |
|:----------:|:---------------:|:-----:|
|
44 |
+
| 8.4168 | 8.5456 | 0 |
|
45 |
+
| 8.0364 | 8.5354 | 1 |
|
46 |
+
| 7.9995 | 8.5982 | 2 |
|
47 |
+
| nan | nan | 3 |
|
48 |
+
| nan | nan | 4 |
|
49 |
+
| nan | nan | 5 |
|
50 |
+
| nan | nan | 6 |
|
51 |
+
| nan | nan | 7 |
|
52 |
+
| nan | nan | 8 |
|
53 |
+
| nan | nan | 9 |
|
54 |
|
55 |
|
56 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 606630176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b45c8900b6b2c96625dd1fa07a0d5024cece9c8f17d719b5ca8243dd0365c14
|
3 |
size 606630176
|