keonju commited on
Commit
876235e
1 Parent(s): 0f5dce5

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -21
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [klue/bert-base](https://huggingface.co/klue/bert-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.0855
23
- - Precision: 0.9424
24
- - Recall: 0.9475
25
- - F1: 0.9449
26
- - Accuracy: 0.9801
27
 
28
  ## Model description
29
 
@@ -43,8 +43,8 @@ More information needed
43
 
44
  The following hyperparameters were used during training:
45
  - learning_rate: 2e-05
46
- - train_batch_size: 30
47
- - eval_batch_size: 30
48
  - seed: 42
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
@@ -52,23 +52,23 @@ The following hyperparameters were used during training:
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
- |:-------------:|:-----:|:------:|:---------------:|:---------:|:------:|:------:|:--------:|
57
- | 0.0663 | 1.0 | 15954 | 0.0599 | 0.9417 | 0.9246 | 0.9331 | 0.9763 |
58
- | 0.0471 | 2.0 | 31908 | 0.0514 | 0.9408 | 0.9442 | 0.9425 | 0.9795 |
59
- | 0.0384 | 3.0 | 47862 | 0.0511 | 0.9419 | 0.9471 | 0.9445 | 0.9802 |
60
- | 0.0292 | 4.0 | 63816 | 0.0558 | 0.9456 | 0.9449 | 0.9453 | 0.9804 |
61
- | 0.0253 | 5.0 | 79770 | 0.0572 | 0.9421 | 0.9507 | 0.9464 | 0.9807 |
62
- | 0.0225 | 6.0 | 95724 | 0.0649 | 0.9474 | 0.9435 | 0.9454 | 0.9805 |
63
- | 0.0209 | 7.0 | 111678 | 0.0695 | 0.9409 | 0.9504 | 0.9456 | 0.9805 |
64
- | 0.019 | 8.0 | 127632 | 0.0742 | 0.9431 | 0.9469 | 0.9450 | 0.9802 |
65
- | 0.0178 | 9.0 | 143586 | 0.0799 | 0.9425 | 0.9477 | 0.9451 | 0.9802 |
66
- | 0.016 | 10.0 | 159540 | 0.0855 | 0.9424 | 0.9475 | 0.9449 | 0.9801 |
67
 
68
 
69
  ### Framework versions
70
 
71
- - Transformers 4.26.0
72
  - Pytorch 1.13.1+cu116
73
- - Datasets 2.9.0
74
  - Tokenizers 0.13.2
 
19
 
20
  This model is a fine-tuned version of [klue/bert-base](https://huggingface.co/klue/bert-base) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.0792
23
+ - Precision: 0.9478
24
+ - Recall: 0.9553
25
+ - F1: 0.9515
26
+ - Accuracy: 0.9879
27
 
28
  ## Model description
29
 
 
43
 
44
  The following hyperparameters were used during training:
45
  - learning_rate: 2e-05
46
+ - train_batch_size: 50
47
+ - eval_batch_size: 50
48
  - seed: 42
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
  - lr_scheduler_type: linear
 
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
+ | 0.1 | 1.0 | 1850 | 0.0461 | 0.9329 | 0.9401 | 0.9365 | 0.9850 |
58
+ | 0.0346 | 2.0 | 3700 | 0.0433 | 0.9367 | 0.9500 | 0.9433 | 0.9864 |
59
+ | 0.0211 | 3.0 | 5550 | 0.0482 | 0.9438 | 0.9493 | 0.9465 | 0.9871 |
60
+ | 0.013 | 4.0 | 7400 | 0.0532 | 0.9449 | 0.9501 | 0.9475 | 0.9869 |
61
+ | 0.0091 | 5.0 | 9250 | 0.0584 | 0.9430 | 0.9549 | 0.9489 | 0.9872 |
62
+ | 0.0063 | 6.0 | 11100 | 0.0675 | 0.9497 | 0.9503 | 0.9500 | 0.9874 |
63
+ | 0.0044 | 7.0 | 12950 | 0.0660 | 0.9467 | 0.9543 | 0.9505 | 0.9876 |
64
+ | 0.0032 | 8.0 | 14800 | 0.0752 | 0.9429 | 0.9563 | 0.9495 | 0.9873 |
65
+ | 0.0025 | 9.0 | 16650 | 0.0766 | 0.9463 | 0.9561 | 0.9512 | 0.9878 |
66
+ | 0.0019 | 10.0 | 18500 | 0.0792 | 0.9478 | 0.9553 | 0.9515 | 0.9879 |
67
 
68
 
69
  ### Framework versions
70
 
71
+ - Transformers 4.26.1
72
  - Pytorch 1.13.1+cu116
73
+ - Datasets 2.10.0
74
  - Tokenizers 0.13.2