Hugging Face's logo

cptanalatriste
/
request-for-help

Text Classification
Transformers
TensorFlow
bert
generated_from_keras_callback
Inference Endpoints
Model card Files Community
1
cptanalatriste commited on
Commit
c3ca23f
·
1 Parent(s): 7636e61

End of training

Browse files
Files changed (2) hide show
  1. README.md +24 -5
  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: 0.8291
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
 
@@ -45,6 +45,25 @@ The following hyperparameters were used during training:
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
 
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: 0.1342
18
+ - Train Sparse Categorical Accuracy: 1.0
19
+ - Validation Loss: 0.1514
20
+ - Validation Sparse Categorical Accuracy: 0.9796
21
+ - Epoch: 19
22
 
23
  ## Model description
24
 
 
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
+ | 0.7470 | 0.375 | 0.6302 | 0.8163 | 1 |
49
+ | 0.6504 | 0.625 | 0.6079 | 0.9184 | 2 |
50
+ | 0.6128 | 0.7812 | 0.5882 | 0.8980 | 3 |
51
+ | 0.5939 | 0.8125 | 0.5639 | 0.9184 | 4 |
52
+ | 0.5300 | 0.9688 | 0.5378 | 0.9184 | 5 |
53
+ | 0.5306 | 0.9688 | 0.5098 | 0.9388 | 6 |
54
+ | 0.4963 | 1.0 | 0.4806 | 0.9388 | 7 |
55
+ | 0.4683 | 0.9688 | 0.4434 | 0.9592 | 8 |
56
+ | 0.3959 | 1.0 | 0.4070 | 0.9796 | 9 |
57
+ | 0.3807 | 1.0 | 0.3762 | 0.9796 | 10 |
58
+ | 0.3509 | 1.0 | 0.3439 | 0.9796 | 11 |
59
+ | 0.3013 | 1.0 | 0.3064 | 0.9796 | 12 |
60
+ | 0.2848 | 1.0 | 0.2931 | 0.9796 | 13 |
61
+ | 0.2587 | 1.0 | 0.2681 | 0.9796 | 14 |
62
+ | 0.2510 | 1.0 | 0.2295 | 0.9796 | 15 |
63
+ | 0.1867 | 1.0 | 0.2000 | 0.9796 | 16 |
64
+ | 0.1652 | 1.0 | 0.1793 | 0.9796 | 17 |
65
+ | 0.1297 | 1.0 | 0.1637 | 0.9796 | 18 |
66
+ | 0.1342 | 1.0 | 0.1514 | 0.9796 | 19 |
67
 
68
 
69
  ### Framework versions
tf_model.h5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e22d4a105f14b1b9d8a979606b49e3cd2d57f874041ae6c80b304201b2f053e1
3
  size 438223192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4abd020d327b6497a1f3efbb5e6b5173b981ae702dc30a65baa189b8eed068e1
3
  size 438223192