Ramuvannela commited on
Commit
45b7999
1 Parent(s): 2f860c2

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +37 -15
README.md CHANGED
@@ -1,22 +1,38 @@
1
  ---
2
  license: apache-2.0
3
  tags:
4
- - generated_from_keras_callback
 
 
 
 
5
  model-index:
6
  - name: bert-fine-tuned-cola
7
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  ---
9
 
10
- <!-- This model card has been generated automatically according to the information Keras had access to. You should
11
- probably proofread and complete it, then remove this comment. -->
12
 
13
  # bert-fine-tuned-cola
14
 
15
- This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Train Loss: 0.2914
18
- - Validation Loss: 0.4224
19
- - Epoch: 1
20
 
21
  ## Model description
22
 
@@ -35,20 +51,26 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': 2e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
39
- - training_precision: float32
 
 
 
 
 
40
 
41
  ### Training results
42
 
43
- | Train Loss | Validation Loss | Epoch |
44
- |:----------:|:---------------:|:-----:|
45
- | 0.4996 | 0.4664 | 0 |
46
- | 0.2914 | 0.4224 | 1 |
 
47
 
48
 
49
  ### Framework versions
50
 
51
  - Transformers 4.26.0
52
- - TensorFlow 2.9.2
53
  - Datasets 2.9.0
54
  - Tokenizers 0.13.2
 
1
  ---
2
  license: apache-2.0
3
  tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - glue
7
+ metrics:
8
+ - matthews_correlation
9
  model-index:
10
  - name: bert-fine-tuned-cola
11
+ results:
12
+ - task:
13
+ name: Text Classification
14
+ type: text-classification
15
+ dataset:
16
+ name: glue
17
+ type: glue
18
+ config: cola
19
+ split: validation
20
+ args: cola
21
+ metrics:
22
+ - name: Matthews Correlation
23
+ type: matthews_correlation
24
+ value: 0.6107419227947289
25
  ---
26
 
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
 
30
  # bert-fine-tuned-cola
31
 
32
+ This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the glue dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.8073
35
+ - Matthews Correlation: 0.6107
 
36
 
37
  ## Model description
38
 
 
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
+ - learning_rate: 2e-05
55
+ - train_batch_size: 8
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 3
61
 
62
  ### Training results
63
 
64
+ | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
66
+ | 0.4681 | 1.0 | 1069 | 0.5613 | 0.4892 |
67
+ | 0.321 | 2.0 | 2138 | 0.6681 | 0.5851 |
68
+ | 0.1781 | 3.0 | 3207 | 0.8073 | 0.6107 |
69
 
70
 
71
  ### Framework versions
72
 
73
  - Transformers 4.26.0
74
+ - Pytorch 1.13.1+cu116
75
  - Datasets 2.9.0
76
  - Tokenizers 0.13.2