felixshier commited on
Commit
2a34271
1 Parent(s): 5479210

Upload TFBertForSequenceClassification

Browse files
Files changed (2) hide show
  1. README.md +8 -8
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -15,9 +15,9 @@ 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: 0.0759
19
- - Validation Loss: 0.7153
20
- - Train F1: 0.8039
21
  - Epoch: 4
22
 
23
  ## Model description
@@ -44,11 +44,11 @@ The following hyperparameters were used during training:
44
 
45
  | Train Loss | Validation Loss | Train F1 | Epoch |
46
  |:----------:|:---------------:|:--------:|:-----:|
47
- | 0.6531 | 0.6153 | 0.7528 | 0 |
48
- | 0.4039 | 0.4978 | 0.8157 | 1 |
49
- | 0.2514 | 0.6096 | 0.7968 | 2 |
50
- | 0.1387 | 0.6281 | 0.8164 | 3 |
51
- | 0.0759 | 0.7153 | 0.8039 | 4 |
52
 
53
 
54
  ### 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: 0.1105
19
+ - Validation Loss: 0.5818
20
+ - Train F1: 0.8327
21
  - Epoch: 4
22
 
23
  ## Model description
 
44
 
45
  | Train Loss | Validation Loss | Train F1 | Epoch |
46
  |:----------:|:---------------:|:--------:|:-----:|
47
+ | 0.6306 | 0.5116 | 0.8177 | 0 |
48
+ | 0.3943 | 0.4783 | 0.8237 | 1 |
49
+ | 0.2692 | 0.4975 | 0.8234 | 2 |
50
+ | 0.1670 | 0.5235 | 0.8305 | 3 |
51
+ | 0.1105 | 0.5818 | 0.8327 | 4 |
52
 
53
 
54
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d61d6625afb786b05cd99b06fa0c18db0c85bc003d0898a395c02c3a7b6bb53
3
  size 438226204
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3de6dc96b0b8c33f2a56d35a5edcf7bc6bcfaab0cb377df166a82180e7b68222
3
  size 438226204