YakovElm commited on
Commit
6346483
·
1 Parent(s): 455130b

Upload TFBertForSequenceClassification

Browse files
Files changed (2) hide show
  1. README.md +7 -7
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,10 +14,10 @@ probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.3772
18
- - Train Accuracy: 0.8444
19
- - Validation Loss: 0.5764
20
- - Validation Accuracy: 0.7454
21
  - Epoch: 2
22
 
23
  ## Model description
@@ -44,9 +44,9 @@ The following hyperparameters were used during training:
44
 
45
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
46
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
47
- | 0.4671 | 0.8196 | 0.5614 | 0.7586 | 0 |
48
- | 0.4299 | 0.8258 | 0.5681 | 0.7586 | 1 |
49
- | 0.3772 | 0.8444 | 0.5764 | 0.7454 | 2 |
50
 
51
 
52
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.3771
18
+ - Train Accuracy: 0.8462
19
+ - Validation Loss: 0.6704
20
+ - Validation Accuracy: 0.7719
21
  - Epoch: 2
22
 
23
  ## Model description
 
44
 
45
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
46
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
47
+ | 0.4746 | 0.8099 | 0.5650 | 0.7586 | 0 |
48
+ | 0.4254 | 0.8258 | 0.5185 | 0.7613 | 1 |
49
+ | 0.3771 | 0.8462 | 0.6704 | 0.7719 | 2 |
50
 
51
 
52
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0822ebdd3b13845bed241174ec3b8d38e4c98ee33c13008e4b645b9af71bc546
3
  size 438223128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de5b823812a84ced3e6c74f9e3d1d0d9449524dcf5baee11a8d51a386560eed3
3
  size 438223128