tkoehlerlg commited on
Commit
2b561b9
·
1 Parent(s): d1b0201

Upload TFBertForSequenceClassification

Browse files
Files changed (2) hide show
  1. README.md +7 -7
  2. 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 [bert-base-german-cased](https://huggingface.co/bert-base-german-cased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.6275
18
- - Validation Loss: 0.6303
19
- - Train Accuracy: 0.7059
20
  - Epoch: 3
21
 
22
  ## Model description
@@ -43,10 +43,10 @@ The following hyperparameters were used during training:
43
 
44
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
45
  |:----------:|:---------------:|:--------------:|:-----:|
46
- | 0.6891 | 0.6542 | 0.5882 | 0 |
47
- | 0.6173 | 0.6303 | 0.7059 | 1 |
48
- | 0.6174 | 0.6303 | 0.7059 | 2 |
49
- | 0.6275 | 0.6303 | 0.7059 | 3 |
50
 
51
 
52
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [bert-base-german-cased](https://huggingface.co/bert-base-german-cased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.5835
18
+ - Validation Loss: 0.6134
19
+ - Train Accuracy: 0.8824
20
  - Epoch: 3
21
 
22
  ## Model description
 
43
 
44
  | Train Loss | Validation Loss | Train Accuracy | Epoch |
45
  |:----------:|:---------------:|:--------------:|:-----:|
46
+ | 0.7155 | 0.6228 | 0.6471 | 0 |
47
+ | 0.5988 | 0.6134 | 0.8824 | 1 |
48
+ | 0.5800 | 0.6134 | 0.8824 | 2 |
49
+ | 0.5835 | 0.6134 | 0.8824 | 3 |
50
 
51
 
52
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4627ac5f0dd283753206ab19d0e1a1cdd1bfed28d3e1242945d175b93e9f6a7e
3
  size 436619544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139a4632329d70f3c492adece793ec3bc6a9359130d42df1b2eb7a8be2992c76
3
  size 436619544