Hugging Face's logo

wcyat
/
bert-suicide-detection-hk

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
wcyat commited on
Commit
9eb24ca
•
1 Parent(s): 3496ba4

Model save

Browse files
Files changed (2) hide show
  1. README.md +57 -32
  2. runs/Jun06_08-48-09_568dee0c5d38/events.out.tfevents.1717663690.568dee0c5d38.6548.3 +2 -2
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 [indiejoseph/bert-base-cantonese](https://huggingface.co/indiejoseph/bert-base-cantonese) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0002
21
- - Accuracy: 1.0
22
 
23
  ## Model description
24
 
@@ -49,38 +49,63 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:------:|:----:|:---------------:|:--------:|
52
- | 0.3468 | 0.1852 | 20 | 0.2052 | 0.9020 |
53
- | 0.2089 | 0.3704 | 40 | 0.1276 | 0.9216 |
54
- | 0.214 | 0.5556 | 60 | 0.0251 | 0.9804 |
55
- | 0.0807 | 0.7407 | 80 | 0.0165 | 0.9804 |
56
- | 0.1064 | 0.9259 | 100 | 0.0031 | 1.0 |
57
- | 0.0134 | 1.1111 | 120 | 0.0025 | 1.0 |
58
- | 0.0349 | 1.2963 | 140 | 0.0007 | 1.0 |
59
- | 0.0819 | 1.4815 | 160 | 0.0706 | 0.9608 |
60
- | 0.0586 | 1.6667 | 180 | 0.0005 | 1.0 |
61
- | 0.0368 | 1.8519 | 200 | 0.0005 | 1.0 |
62
- | 0.0485 | 2.0370 | 220 | 0.0031 | 1.0 |
63
- | 0.017 | 2.2222 | 240 | 0.0003 | 1.0 |
64
- | 0.0017 | 2.4074 | 260 | 0.0021 | 1.0 |
65
- | 0.0004 | 2.5926 | 280 | 0.0004 | 1.0 |
66
- | 0.0444 | 2.7778 | 300 | 0.0003 | 1.0 |
67
- | 0.0005 | 2.9630 | 320 | 0.0003 | 1.0 |
68
- | 0.0003 | 3.1481 | 340 | 0.0002 | 1.0 |
69
- | 0.0238 | 3.3333 | 360 | 0.0003 | 1.0 |
70
- | 0.0003 | 3.5185 | 380 | 0.0002 | 1.0 |
71
- | 0.0003 | 3.7037 | 400 | 0.0002 | 1.0 |
72
- | 0.0003 | 3.8889 | 420 | 0.0002 | 1.0 |
73
- | 0.0007 | 4.0741 | 440 | 0.0002 | 1.0 |
74
- | 0.0002 | 4.2593 | 460 | 0.0002 | 1.0 |
75
- | 0.0003 | 4.4444 | 480 | 0.0002 | 1.0 |
76
- | 0.0002 | 4.6296 | 500 | 0.0002 | 1.0 |
77
- | 0.0002 | 4.8148 | 520 | 0.0002 | 1.0 |
78
- | 0.0002 | 5.0 | 540 | 0.0002 | 1.0 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
79
 
80
 
81
  ### Framework versions
82
 
83
- - Transformers 4.41.1
84
- - Pytorch 2.1.2
85
- - Datasets 2.19.1
86
  - Tokenizers 0.19.1
 
17
 
18
  This model is a fine-tuned version of [indiejoseph/bert-base-cantonese](https://huggingface.co/indiejoseph/bert-base-cantonese) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.1071
21
+ - Accuracy: 0.9785
22
 
23
  ## Model description
24
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
51
  |:-------------:|:------:|:----:|:---------------:|:--------:|
52
+ | 0.5169 | 0.0962 | 20 | 0.4365 | 0.8065 |
53
+ | 0.3487 | 0.1923 | 40 | 0.3232 | 0.8602 |
54
+ | 0.1785 | 0.2885 | 60 | 0.1470 | 0.9462 |
55
+ | 0.192 | 0.3846 | 80 | 0.1264 | 0.9570 |
56
+ | 0.0329 | 0.4808 | 100 | 0.1857 | 0.9570 |
57
+ | 0.1432 | 0.5769 | 120 | 0.2023 | 0.9247 |
58
+ | 0.3458 | 0.6731 | 140 | 0.1269 | 0.9677 |
59
+ | 0.234 | 0.7692 | 160 | 0.1510 | 0.9462 |
60
+ | 0.179 | 0.8654 | 180 | 0.1102 | 0.9677 |
61
+ | 0.1873 | 0.9615 | 200 | 0.1140 | 0.9570 |
62
+ | 0.1519 | 1.0577 | 220 | 0.2102 | 0.9462 |
63
+ | 0.0453 | 1.1538 | 240 | 0.3150 | 0.9247 |
64
+ | 0.0341 | 1.25 | 260 | 0.1401 | 0.9570 |
65
+ | 0.0316 | 1.3462 | 280 | 0.1634 | 0.9677 |
66
+ | 0.1082 | 1.4423 | 300 | 0.1069 | 0.9785 |
67
+ | 0.0954 | 1.5385 | 320 | 0.0819 | 0.9785 |
68
+ | 0.0472 | 1.6346 | 340 | 0.1686 | 0.9677 |
69
+ | 0.1563 | 1.7308 | 360 | 0.0379 | 0.9785 |
70
+ | 0.1812 | 1.8269 | 380 | 0.1218 | 0.9677 |
71
+ | 0.1276 | 1.9231 | 400 | 0.0785 | 0.9892 |
72
+ | 0.0772 | 2.0192 | 420 | 0.0788 | 0.9892 |
73
+ | 0.0022 | 2.1154 | 440 | 0.1028 | 0.9570 |
74
+ | 0.0011 | 2.2115 | 460 | 0.1562 | 0.9570 |
75
+ | 0.076 | 2.3077 | 480 | 0.1219 | 0.9785 |
76
+ | 0.0012 | 2.4038 | 500 | 0.1159 | 0.9570 |
77
+ | 0.1572 | 2.5 | 520 | 0.0987 | 0.9785 |
78
+ | 0.0359 | 2.5962 | 540 | 0.1208 | 0.9785 |
79
+ | 0.0737 | 2.6923 | 560 | 0.0974 | 0.9785 |
80
+ | 0.1555 | 2.7885 | 580 | 0.1363 | 0.9785 |
81
+ | 0.0928 | 2.8846 | 600 | 0.0681 | 0.9785 |
82
+ | 0.0008 | 2.9808 | 620 | 0.0611 | 0.9677 |
83
+ | 0.0606 | 3.0769 | 640 | 0.0979 | 0.9785 |
84
+ | 0.0693 | 3.1731 | 660 | 0.0768 | 0.9677 |
85
+ | 0.0005 | 3.2692 | 680 | 0.0925 | 0.9677 |
86
+ | 0.0006 | 3.3654 | 700 | 0.0922 | 0.9677 |
87
+ | 0.0005 | 3.4615 | 720 | 0.0907 | 0.9677 |
88
+ | 0.0004 | 3.5577 | 740 | 0.0923 | 0.9677 |
89
+ | 0.056 | 3.6538 | 760 | 0.0906 | 0.9570 |
90
+ | 0.0006 | 3.75 | 780 | 0.0913 | 0.9785 |
91
+ | 0.056 | 3.8462 | 800 | 0.1173 | 0.9785 |
92
+ | 0.0005 | 3.9423 | 820 | 0.1341 | 0.9785 |
93
+ | 0.0004 | 4.0385 | 840 | 0.1199 | 0.9785 |
94
+ | 0.0004 | 4.1346 | 860 | 0.1161 | 0.9785 |
95
+ | 0.0003 | 4.2308 | 880 | 0.1156 | 0.9785 |
96
+ | 0.0385 | 4.3269 | 900 | 0.0859 | 0.9785 |
97
+ | 0.0028 | 4.4231 | 920 | 0.0961 | 0.9785 |
98
+ | 0.0003 | 4.5192 | 940 | 0.1021 | 0.9785 |
99
+ | 0.0014 | 4.6154 | 960 | 0.1071 | 0.9785 |
100
+ | 0.0003 | 4.7115 | 980 | 0.1089 | 0.9785 |
101
+ | 0.0003 | 4.8077 | 1000 | 0.1082 | 0.9785 |
102
+ | 0.0576 | 4.9038 | 1020 | 0.1066 | 0.9785 |
103
+ | 0.0003 | 5.0 | 1040 | 0.1071 | 0.9785 |
104
 
105
 
106
  ### Framework versions
107
 
108
+ - Transformers 4.41.2
109
+ - Pytorch 2.3.0+cu121
110
+ - Datasets 2.19.2
111
  - Tokenizers 0.19.1
runs/Jun06_08-48-09_568dee0c5d38/events.out.tfevents.1717663690.568dee0c5d38.6548.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b90b6812b2da680d6eef4248597790faae5bdfa18079d5a784feed3395fe2f9d
3
- size 31640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71e8842bf11aa5f32a398a2e3488e8f012f7f22db568750fb0649b115a70aaee
3
+ size 33062