Hugging Face's logo

irfanamal
/
bert_multiple_choice

Multiple Choice
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
1
irfanamal commited on
Commit
8d930fb
·
1 Parent(s): da859f0

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +34 -17
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.7699
21
- - Accuracy: 0.4
22
 
23
  ## Model description
24
 
@@ -37,31 +37,48 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 5e-05
41
  - train_batch_size: 16
42
  - eval_batch_size: 16
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
- - num_epochs: 30
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
- | No log | 1.0 | 12 | 1.5847 | 0.35 |
53
- | No log | 2.0 | 24 | 1.5755 | 0.4 |
54
- | No log | 3.0 | 36 | 1.5319 | 0.4 |
55
- | No log | 4.0 | 48 | 1.4726 | 0.25 |
56
- | No log | 5.0 | 60 | 1.4044 | 0.35 |
57
- | No log | 6.0 | 72 | 1.4757 | 0.4 |
58
- | No log | 7.0 | 84 | 1.4304 | 0.35 |
59
- | No log | 8.0 | 96 | 1.3443 | 0.4 |
60
- | No log | 9.0 | 108 | 1.4260 | 0.4 |
61
- | No log | 10.0 | 120 | 1.3992 | 0.35 |
62
- | No log | 11.0 | 132 | 1.4580 | 0.35 |
63
- | No log | 12.0 | 144 | 1.4976 | 0.3 |
64
- | No log | 13.0 | 156 | 1.7699 | 0.4 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65
 
66
 
67
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.3676
21
+ - Accuracy: 0.45
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 5e-06
41
  - train_batch_size: 16
42
  - eval_batch_size: 16
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 50
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
52
+ | No log | 1.0 | 12 | 1.6011 | 0.2 |
53
+ | No log | 2.0 | 24 | 1.6026 | 0.2 |
54
+ | No log | 3.0 | 36 | 1.5957 | 0.3 |
55
+ | No log | 4.0 | 48 | 1.5885 | 0.35 |
56
+ | No log | 5.0 | 60 | 1.5782 | 0.4 |
57
+ | No log | 6.0 | 72 | 1.5609 | 0.45 |
58
+ | No log | 7.0 | 84 | 1.5448 | 0.45 |
59
+ | No log | 8.0 | 96 | 1.5432 | 0.45 |
60
+ | No log | 9.0 | 108 | 1.5166 | 0.5 |
61
+ | No log | 10.0 | 120 | 1.5045 | 0.5 |
62
+ | No log | 11.0 | 132 | 1.5056 | 0.5 |
63
+ | No log | 12.0 | 144 | 1.5011 | 0.5 |
64
+ | No log | 13.0 | 156 | 1.5010 | 0.4 |
65
+ | No log | 14.0 | 168 | 1.4879 | 0.4 |
66
+ | No log | 15.0 | 180 | 1.4721 | 0.5 |
67
+ | No log | 16.0 | 192 | 1.4582 | 0.45 |
68
+ | No log | 17.0 | 204 | 1.4659 | 0.5 |
69
+ | No log | 18.0 | 216 | 1.4445 | 0.4 |
70
+ | No log | 19.0 | 228 | 1.4404 | 0.45 |
71
+ | No log | 20.0 | 240 | 1.4322 | 0.45 |
72
+ | No log | 21.0 | 252 | 1.4284 | 0.4 |
73
+ | No log | 22.0 | 264 | 1.4045 | 0.45 |
74
+ | No log | 23.0 | 276 | 1.3910 | 0.5 |
75
+ | No log | 24.0 | 288 | 1.4120 | 0.45 |
76
+ | No log | 25.0 | 300 | 1.3679 | 0.5 |
77
+ | No log | 26.0 | 312 | 1.3662 | 0.5 |
78
+ | No log | 27.0 | 324 | 1.3865 | 0.55 |
79
+ | No log | 28.0 | 336 | 1.4005 | 0.5 |
80
+ | No log | 29.0 | 348 | 1.3866 | 0.45 |
81
+ | No log | 30.0 | 360 | 1.3676 | 0.45 |
82
 
83
 
84
  ### Framework versions