YakovElm commited on
Commit
ec81284
·
1 Parent(s): 8af8ea2

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: 0.1578
18
- - Train Accuracy: 0.8916
19
- - Validation Loss: 0.2509
20
- - Validation Accuracy: 0.8395
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
- | 0.2021 | 0.8803 | 0.2311 | 0.8414 | 0 |
48
- | 0.1890 | 0.8810 | 0.2269 | 0.8429 | 1 |
49
- | 0.1578 | 0.8916 | 0.2509 | 0.8395 | 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: 0.1467
18
+ - Train Accuracy: 0.9022
19
+ - Validation Loss: 0.2326
20
+ - Validation Accuracy: 0.8410
21
  - Epoch: 2
22
 
23
  ## Model description
 
44
 
45
  | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
46
  |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
47
+ | 0.2020 | 0.8796 | 0.2298 | 0.8414 | 0 |
48
+ | 0.1825 | 0.8818 | 0.2321 | 0.8362 | 1 |
49
+ | 0.1467 | 0.9022 | 0.2326 | 0.8410 | 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 sha256:61b1b552f8cd08ba4404c0f58a5704f01cb50a93d655c79e52f4a28105eeb957
3
  size 438223128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84b6544214c77952ba9565cc202e8ee1e84e56c335b08d61d4aaf71f429b0b1e
3
  size 438223128