Hugging Face's logo

cptanalatriste
/
request-for-help

Text Classification
Transformers
TensorFlow
bert
generated_from_keras_callback
text-embeddings-inference
Model card Files
xet
 Community
1
cptanalatriste commited on
Commit
7636e61
·
1 Parent(s): a30ef94

Training in progress epoch 0

Browse files
Files changed (2) hide show
  1. README.md +6 -25
  2. tf_model.h5 +1 -1
README.md CHANGED
@@ -14,11 +14,11 @@ 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: 0.0591
18
- - Train Sparse Categorical Accuracy: 1.0
19
- - Validation Loss: 0.1014
20
- - Validation Sparse Categorical Accuracy: 0.9796
21
- - Epoch: 19
22
 
23
  ## Model description
24
 
@@ -44,26 +44,7 @@ The following hyperparameters were used during training:
44
 
45
  | Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
46
  |:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
47
- | 0.6625 | 0.6562 | 0.6432 | 0.6327 | 0 |
48
- | 0.6527 | 0.5938 | 0.6170 | 0.6735 | 1 |
49
- | 0.6059 | 0.7188 | 0.5768 | 0.7143 | 2 |
50
- | 0.5976 | 0.75 | 0.5263 | 0.7959 | 3 |
51
- | 0.5440 | 0.6875 | 0.4785 | 0.7959 | 4 |
52
- | 0.4520 | 0.9062 | 0.4446 | 0.7959 | 5 |
53
- | 0.4385 | 0.875 | 0.4008 | 0.8571 | 6 |
54
- | 0.3452 | 0.9375 | 0.3540 | 0.8980 | 7 |
55
- | 0.3535 | 0.9375 | 0.2996 | 0.9592 | 8 |
56
- | 0.3029 | 0.9688 | 0.2533 | 0.9796 | 9 |
57
- | 0.2292 | 1.0 | 0.2184 | 0.9796 | 10 |
58
- | 0.1828 | 1.0 | 0.1874 | 0.9796 | 11 |
59
- | 0.1986 | 0.9688 | 0.1646 | 0.9796 | 12 |
60
- | 0.1715 | 0.9688 | 0.1519 | 0.9796 | 13 |
61
- | 0.1558 | 0.9688 | 0.1440 | 0.9796 | 14 |
62
- | 0.1399 | 0.9688 | 0.1380 | 0.9796 | 15 |
63
- | 0.1199 | 1.0 | 0.1325 | 0.9796 | 16 |
64
- | 0.0987 | 1.0 | 0.1229 | 0.9796 | 17 |
65
- | 0.0787 | 1.0 | 0.1113 | 0.9796 | 18 |
66
- | 0.0591 | 1.0 | 0.1014 | 0.9796 | 19 |
67
 
68
 
69
  ### 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: 0.8291
18
+ - Train Sparse Categorical Accuracy: 0.375
19
+ - Validation Loss: 0.7483
20
+ - Validation Sparse Categorical Accuracy: 0.3673
21
+ - Epoch: 0
22
 
23
  ## Model description
24
 
 
44
 
45
  | Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
46
  |:----------:|:---------------------------------:|:---------------:|:--------------------------------------:|:-----:|
47
+ | 0.8291 | 0.375 | 0.7483 | 0.3673 | 0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
 
49
 
50
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1427dbd3ed2c1c6aac27223dd7b65f828aac9fa885843c92676ff52a5d38b110
3
  size 438223192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e22d4a105f14b1b9d8a979606b49e3cd2d57f874041ae6c80b304201b2f053e1
3
  size 438223192