simonycl commited on
Commit
4988b60
1 Parent(s): 8374dc0

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -32
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 an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.5860
21
- - Accuracy: 0.7344
22
 
23
  ## Model description
24
 
@@ -50,36 +50,36 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
- | No log | 1.0 | 2 | 0.7504 | 0.4844 |
54
- | No log | 2.0 | 4 | 0.7296 | 0.4844 |
55
- | No log | 3.0 | 6 | 0.7038 | 0.4688 |
56
- | No log | 4.0 | 8 | 0.6848 | 0.5 |
57
- | 0.6775 | 5.0 | 10 | 0.6753 | 0.5312 |
58
- | 0.6775 | 6.0 | 12 | 0.6666 | 0.5625 |
59
- | 0.6775 | 7.0 | 14 | 0.6533 | 0.5938 |
60
- | 0.6775 | 8.0 | 16 | 0.6361 | 0.6406 |
61
- | 0.6775 | 9.0 | 18 | 0.6181 | 0.6562 |
62
- | 0.4471 | 10.0 | 20 | 0.6136 | 0.6406 |
63
- | 0.4471 | 11.0 | 22 | 0.6116 | 0.6875 |
64
- | 0.4471 | 12.0 | 24 | 0.6051 | 0.7031 |
65
- | 0.4471 | 13.0 | 26 | 0.5977 | 0.7031 |
66
- | 0.4471 | 14.0 | 28 | 0.5903 | 0.7031 |
67
- | 0.2163 | 15.0 | 30 | 0.5855 | 0.7031 |
68
- | 0.2163 | 16.0 | 32 | 0.5839 | 0.7031 |
69
- | 0.2163 | 17.0 | 34 | 0.5831 | 0.7031 |
70
- | 0.2163 | 18.0 | 36 | 0.5821 | 0.7031 |
71
- | 0.2163 | 19.0 | 38 | 0.5822 | 0.7188 |
72
- | 0.1269 | 20.0 | 40 | 0.5819 | 0.7188 |
73
- | 0.1269 | 21.0 | 42 | 0.5826 | 0.7188 |
74
- | 0.1269 | 22.0 | 44 | 0.5844 | 0.7344 |
75
- | 0.1269 | 23.0 | 46 | 0.5848 | 0.7344 |
76
- | 0.1269 | 24.0 | 48 | 0.5841 | 0.75 |
77
- | 0.0961 | 25.0 | 50 | 0.5841 | 0.7344 |
78
- | 0.0961 | 26.0 | 52 | 0.5848 | 0.7344 |
79
- | 0.0961 | 27.0 | 54 | 0.5854 | 0.7344 |
80
- | 0.0961 | 28.0 | 56 | 0.5858 | 0.7344 |
81
- | 0.0961 | 29.0 | 58 | 0.5859 | 0.7344 |
82
- | 0.0833 | 30.0 | 60 | 0.5860 | 0.7344 |
83
 
84
 
85
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.5572
21
+ - Accuracy: 0.75
22
 
23
  ## Model description
24
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | No log | 1.0 | 2 | 0.6997 | 0.4375 |
54
+ | No log | 2.0 | 4 | 0.6973 | 0.4375 |
55
+ | No log | 3.0 | 6 | 0.6912 | 0.5781 |
56
+ | No log | 4.0 | 8 | 0.6876 | 0.5 |
57
+ | 0.6783 | 5.0 | 10 | 0.6843 | 0.5312 |
58
+ | 0.6783 | 6.0 | 12 | 0.6800 | 0.5781 |
59
+ | 0.6783 | 7.0 | 14 | 0.6738 | 0.5938 |
60
+ | 0.6783 | 8.0 | 16 | 0.6662 | 0.6562 |
61
+ | 0.6783 | 9.0 | 18 | 0.6573 | 0.6562 |
62
+ | 0.5945 | 10.0 | 20 | 0.6496 | 0.7031 |
63
+ | 0.5945 | 11.0 | 22 | 0.6427 | 0.7188 |
64
+ | 0.5945 | 12.0 | 24 | 0.6343 | 0.7188 |
65
+ | 0.5945 | 13.0 | 26 | 0.6270 | 0.7031 |
66
+ | 0.5945 | 14.0 | 28 | 0.6218 | 0.6875 |
67
+ | 0.4805 | 15.0 | 30 | 0.6166 | 0.6875 |
68
+ | 0.4805 | 16.0 | 32 | 0.6110 | 0.7188 |
69
+ | 0.4805 | 17.0 | 34 | 0.6046 | 0.7344 |
70
+ | 0.4805 | 18.0 | 36 | 0.5972 | 0.7344 |
71
+ | 0.4805 | 19.0 | 38 | 0.5895 | 0.7344 |
72
+ | 0.3522 | 20.0 | 40 | 0.5823 | 0.75 |
73
+ | 0.3522 | 21.0 | 42 | 0.5767 | 0.7344 |
74
+ | 0.3522 | 22.0 | 44 | 0.5708 | 0.7344 |
75
+ | 0.3522 | 23.0 | 46 | 0.5667 | 0.7344 |
76
+ | 0.3522 | 24.0 | 48 | 0.5637 | 0.7344 |
77
+ | 0.2697 | 25.0 | 50 | 0.5616 | 0.7344 |
78
+ | 0.2697 | 26.0 | 52 | 0.5603 | 0.7344 |
79
+ | 0.2697 | 27.0 | 54 | 0.5592 | 0.7344 |
80
+ | 0.2697 | 28.0 | 56 | 0.5582 | 0.75 |
81
+ | 0.2697 | 29.0 | 58 | 0.5574 | 0.75 |
82
+ | 0.2363 | 30.0 | 60 | 0.5572 | 0.75 |
83
 
84
 
85
  ### Framework versions