Hugging Face's logo

minoosh
/
finetuned_bert-base-uncased

Text Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
minoosh commited on
Commit
b68530f
•
1 Parent(s): f3af2c1

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +27 -21
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.9064
20
- - Accuracy: 0.6591
21
 
22
  ## Model description
23
 
@@ -37,37 +37,43 @@ More information needed
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 2e-05
40
- - train_batch_size: 16
41
- - eval_batch_size: 16
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
- - num_epochs: 15
 
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
- | No log | 1.0 | 204 | 0.9670 | 0.6052 |
52
- | No log | 2.0 | 408 | 0.8899 | 0.6731 |
53
- | 0.8476 | 3.0 | 612 | 0.9283 | 0.6722 |
54
- | 0.8476 | 4.0 | 816 | 1.0110 | 0.6828 |
55
- | 0.3419 | 5.0 | 1020 | 1.0947 | 0.6741 |
56
- | 0.3419 | 6.0 | 1224 | 1.1896 | 0.6799 |
57
- | 0.3419 | 7.0 | 1428 | 1.3467 | 0.6887 |
58
- | 0.193 | 8.0 | 1632 | 1.3716 | 0.6838 |
59
- | 0.193 | 9.0 | 1836 | 1.4742 | 0.6809 |
60
- | 0.1485 | 10.0 | 2040 | 1.5121 | 0.6867 |
61
- | 0.1485 | 11.0 | 2244 | 1.5670 | 0.6819 |
62
- | 0.1485 | 12.0 | 2448 | 1.5593 | 0.6867 |
63
- | 0.1185 | 13.0 | 2652 | 1.6455 | 0.6809 |
64
- | 0.1185 | 14.0 | 2856 | 1.6417 | 0.6877 |
65
- | 0.1077 | 15.0 | 3060 | 1.6399 | 0.6867 |
 
 
 
 
 
66
 
67
 
68
  ### Framework versions
69
 
70
  - Transformers 4.26.1
71
  - Pytorch 1.13.1+cu116
72
- - Datasets 2.10.0
73
  - Tokenizers 0.13.2
 
16
 
17
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.1947
20
+ - Accuracy: 0.6793
21
 
22
  ## Model description
23
 
 
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 2e-05
40
+ - train_batch_size: 32
41
+ - eval_batch_size: 32
42
  - seed: 42
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_ratio: 0.1
46
+ - num_epochs: 20
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | 1.2761 | 1.0 | 102 | 1.3225 | 0.3375 |
53
+ | 0.9847 | 2.0 | 204 | 1.0792 | 0.5509 |
54
+ | 0.6882 | 3.0 | 306 | 0.9260 | 0.6382 |
55
+ | 0.5099 | 4.0 | 408 | 0.9072 | 0.6634 |
56
+ | 0.4614 | 5.0 | 510 | 0.9115 | 0.6867 |
57
+ | 0.3406 | 6.0 | 612 | 1.0022 | 0.6751 |
58
+ | 0.189 | 7.0 | 714 | 1.0881 | 0.6751 |
59
+ | 0.2179 | 8.0 | 816 | 1.1520 | 0.6712 |
60
+ | 0.2085 | 9.0 | 918 | 1.2567 | 0.6896 |
61
+ | 0.1914 | 10.0 | 1020 | 1.2074 | 0.6828 |
62
+ | 0.1271 | 11.0 | 1122 | 1.3389 | 0.6887 |
63
+ | 0.1236 | 12.0 | 1224 | 1.3539 | 0.6790 |
64
+ | 0.0946 | 13.0 | 1326 | 1.4042 | 0.6838 |
65
+ | 0.0968 | 14.0 | 1428 | 1.4079 | 0.6877 |
66
+ | 0.1095 | 15.0 | 1530 | 1.4884 | 0.6799 |
67
+ | 0.1102 | 16.0 | 1632 | 1.5244 | 0.6790 |
68
+ | 0.1159 | 17.0 | 1734 | 1.5238 | 0.6799 |
69
+ | 0.1448 | 18.0 | 1836 | 1.5568 | 0.6780 |
70
+ | 0.1105 | 19.0 | 1938 | 1.5629 | 0.6780 |
71
+ | 0.092 | 20.0 | 2040 | 1.5588 | 0.6809 |
72
 
73
 
74
  ### Framework versions
75
 
76
  - Transformers 4.26.1
77
  - Pytorch 1.13.1+cu116
78
+ - Datasets 2.10.1
79
  - Tokenizers 0.13.2