Upload TFBertForMaskedLM
Browse files- README.md +13 -4
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
-
base_model: google-bert/bert-base-german-cased
|
3 |
license: mit
|
|
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
@@ -15,8 +15,8 @@ probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [google-bert/bert-base-german-cased](https://huggingface.co/google-bert/bert-base-german-cased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss:
|
19 |
-
- Epoch:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -42,7 +42,16 @@ The following hyperparameters were used during training:
|
|
42 |
|
43 |
| Train Loss | Epoch |
|
44 |
|:----------:|:-----:|
|
45 |
-
| 2.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
|
|
1 |
---
|
|
|
2 |
license: mit
|
3 |
+
base_model: google-bert/bert-base-german-cased
|
4 |
tags:
|
5 |
- generated_from_keras_callback
|
6 |
model-index:
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [google-bert/bert-base-german-cased](https://huggingface.co/google-bert/bert-base-german-cased) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 1.2900
|
19 |
+
- Epoch: 9
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
42 |
|
43 |
| Train Loss | Epoch |
|
44 |
|:----------:|:-----:|
|
45 |
+
| 2.4250 | 0 |
|
46 |
+
| 1.3110 | 1 |
|
47 |
+
| 1.3098 | 2 |
|
48 |
+
| 1.3043 | 3 |
|
49 |
+
| 1.3020 | 4 |
|
50 |
+
| 1.3002 | 5 |
|
51 |
+
| 1.2968 | 6 |
|
52 |
+
| 1.2929 | 7 |
|
53 |
+
| 1.2927 | 8 |
|
54 |
+
| 1.2900 | 9 |
|
55 |
|
56 |
|
57 |
### Framework versions
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 530478360
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2848689bc738e4211f36ea00acce577836c1d84ff14b8dc909b426a52ce7f04e
|
3 |
size 530478360
|