YakovElm commited on
Commit
9ae1721
·
1 Parent(s): 737516c

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: 0.5202
18
- - Train Accuracy: 0.7463
19
- - Validation Loss: 0.5731
20
- - Validation Accuracy: 0.7301
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
- | 0.6224 | 0.6844 | 0.6100 | 0.6195 | 0 |
48
- | 0.5779 | 0.7198 | 0.5530 | 0.7257 | 1 |
49
- | 0.5202 | 0.7463 | 0.5731 | 0.7301 | 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: 0.5301
18
+ - Train Accuracy: 0.7227
19
+ - Validation Loss: 0.6836
20
+ - Validation Accuracy: 0.6947
21
  - Epoch: 2
22
 
23
  ## Model description
 
44
 
45
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
46
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
47
+ | 0.6315 | 0.6667 | 0.6081 | 0.6726 | 0 |
48
+ | 0.5750 | 0.6962 | 0.6117 | 0.6549 | 1 |
49
+ | 0.5301 | 0.7227 | 0.6836 | 0.6947 | 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:a997564f27dd1df72969747bf7bce784ff6ec19b3901601e8f68838689f985a6
3
  size 438223128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8731e1df1b71d21519d17ddc0096100e688fa3371f4251429e2f069087dd3dd
3
  size 438223128