YakovElm commited on
Commit
2dd793a
·
1 Parent(s): eea4e90

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: 0.3816
18
- - Train Accuracy: 0.8407
19
- - Validation Loss: 0.4673
20
- - Validation Accuracy: 0.7583
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
- | 0.5409 | 0.7511 | 0.4774 | 0.7748 | 0 |
48
- | 0.4796 | 0.7920 | 0.4688 | 0.7715 | 1 |
49
- | 0.3816 | 0.8407 | 0.4673 | 0.7583 | 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: 0.4946
18
+ - Train Accuracy: 0.7478
19
+ - Validation Loss: 0.4568
20
+ - Validation Accuracy: 0.7649
21
  - Epoch: 2
22
 
23
  ## Model description
 
44
 
45
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
46
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
47
+ | 0.5508 | 0.7489 | 0.4948 | 0.7616 | 0 |
48
+ | 0.5171 | 0.7533 | 0.4904 | 0.7616 | 1 |
49
+ | 0.4946 | 0.7478 | 0.4568 | 0.7649 | 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 sha256:55ea7bc97553365913542c085ec23cc680da25f0f126820f76201efd62b1b179
3
  size 438223128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cd17b4e7922e19de4f73ad24b5d591b888919119f6a2fe8a847d88dcddf237e
3
  size 438223128