felixshier commited on
Commit
43e7e81
1 Parent(s): e13a80a

Upload TFBertForSequenceClassification

Browse files
Files changed (2) hide show
  1. README.md +8 -7
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,10 +15,10 @@ probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Train Loss: 0.6564
19
- - Validation Loss: 0.6941
20
- - Train Precision: 0.3333
21
- - Epoch: 2
22
 
23
  ## Model description
24
 
@@ -44,9 +44,10 @@ The following hyperparameters were used during training:
44
 
45
  | Train Loss | Validation Loss | Train Precision | Epoch |
46
  |:----------:|:---------------:|:---------------:|:-----:|
47
- | 0.7024 | 0.6867 | 0.55 | 0 |
48
- | 0.6780 | 0.6944 | 0.5 | 1 |
49
- | 0.6564 | 0.6941 | 0.3333 | 2 |
 
50
 
51
 
52
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Train Loss: 0.6295
19
+ - Validation Loss: 0.7210
20
+ - Train Precision: 0.38
21
+ - Epoch: 3
22
 
23
  ## Model description
24
 
 
44
 
45
  | Train Loss | Validation Loss | Train Precision | Epoch |
46
  |:----------:|:---------------:|:---------------:|:-----:|
47
+ | 0.7161 | 0.7021 | 0.4118 | 0 |
48
+ | 0.6906 | 0.7071 | 0.4730 | 1 |
49
+ | 0.6443 | 0.7257 | 0.3333 | 2 |
50
+ | 0.6295 | 0.7210 | 0.38 | 3 |
51
 
52
 
53
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28fc5a34e5abed766a557f72ab36f0ec4676d6ff7e161225449d91e9e0a11eb9
3
  size 438223128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdf6c19dc9d773cf4a824344a2f2fe5abf934e91bcbec1cd5d6def525adbe1a7
3
  size 438223128