YakovElm commited on
Commit
41a745e
·
1 Parent(s): 9160467

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: 0.5717
18
- - Train Accuracy: 0.7037
19
- - Validation Loss: 0.6161
20
- - Validation Accuracy: 0.6349
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
- | 0.6389 | 0.6190 | 0.6208 | 0.6667 | 0 |
48
- | 0.5868 | 0.6878 | 0.5984 | 0.6825 | 1 |
49
- | 0.5717 | 0.7037 | 0.6161 | 0.6349 | 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: 0.5860
18
+ - Train Accuracy: 0.6772
19
+ - Validation Loss: 0.6540
20
+ - Validation Accuracy: 0.6667
21
  - Epoch: 2
22
 
23
  ## Model description
 
44
 
45
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
46
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
47
+ | 0.6459 | 0.6455 | 0.6410 | 0.6667 | 0 |
48
+ | 0.6023 | 0.6825 | 0.6514 | 0.6190 | 1 |
49
+ | 0.5860 | 0.6772 | 0.6540 | 0.6667 | 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 sha256:466a31a2a863aa8abef2ed8637abf6d110ebf06088f632a3adc96e1e48a77ba1
3
  size 438223128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72ccb7b43dc3b87a0726394c7133e8ae172fee7a975f2ccdc0c4bcc5195d2b7b
3
  size 438223128