Hugging Face's logo

EmincanY
/
bert-base-cased

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
Community
1
EmincanY commited on
Commit
045db7d
·
1 Parent(s): d833440

End of training2

Browse files
Files changed (2) hide show
  1. README.md +13 -10
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -20,7 +20,7 @@ model-index:
20
  metrics:
21
  - name: Matthews Correlation
22
  type: matthews_correlation
23
- value: 0.5828920064390912
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,8 +30,8 @@ should probably proofread and complete it, then remove this comment. -->
30
 
31
  This model was trained from scratch on the glue dataset.
32
  It achieves the following results on the evaluation set:
33
- - Loss: 1.1275
34
- - Matthews Correlation: 0.5829
35
 
36
  ## Model description
37
 
@@ -50,21 +50,24 @@ More information needed
50
  ### Training hyperparameters
51
 
52
  The following hyperparameters were used during training:
53
- - learning_rate: 2e-05
54
- - train_batch_size: 8
55
- - eval_batch_size: 8
56
  - seed: 42
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: linear
59
- - num_epochs: 3
60
 
61
  ### Training results
62
 
63
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
64
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
65
- | 0.1801 | 1.0 | 1069 | 0.9499 | 0.5500 |
66
- | 0.1127 | 2.0 | 2138 | 0.9843 | 0.5650 |
67
- | 0.0764 | 3.0 | 3207 | 1.1275 | 0.5829 |
 
 
 
68
 
69
 
70
  ### Framework versions
 
20
  metrics:
21
  - name: Matthews Correlation
22
  type: matthews_correlation
23
+ value: 0.5722385869866928
24
  ---
25
 
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
30
 
31
  This model was trained from scratch on the glue dataset.
32
  It achieves the following results on the evaluation set:
33
+ - Loss: 1.2998
34
+ - Matthews Correlation: 0.5722
35
 
36
  ## Model description
37
 
 
50
  ### Training hyperparameters
51
 
52
  The following hyperparameters were used during training:
53
+ - learning_rate: 2e-06
54
+ - train_batch_size: 16
55
+ - eval_batch_size: 16
56
  - seed: 42
57
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
58
  - lr_scheduler_type: linear
59
+ - num_epochs: 6
60
 
61
  ### Training results
62
 
63
  | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
64
  |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
65
+ | 0.0583 | 1.0 | 535 | 1.1800 | 0.5645 |
66
+ | 0.0418 | 2.0 | 1070 | 1.1857 | 0.5769 |
67
+ | 0.0282 | 3.0 | 1605 | 1.2021 | 0.5863 |
68
+ | 0.0326 | 4.0 | 2140 | 1.2754 | 0.5697 |
69
+ | 0.0291 | 5.0 | 2675 | 1.2999 | 0.5717 |
70
+ | 0.0275 | 6.0 | 3210 | 1.2998 | 0.5722 |
71
 
72
 
73
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0bcaab422947956151a3c1fb9af90adef4798c52b1a8821c70af2f5297d80ce
3
  size 433315633
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90e10e6d0276a6aad548bbc1270dea54fca6979b3e6def4ec6a0d71a177ea557
3
  size 433315633