Hugging Face's logo

wcyat
/
bert-suicide-detection-hk-large-new

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
wcyat commited on
Commit
d9dc4eb
·
verified ·
1 Parent(s): 33b5c40

Model save

Browse files
Files changed (1) hide show
  1. README.md +40 -89
README.md CHANGED
@@ -1,25 +1,25 @@
1
  ---
2
  library_name: transformers
3
- license: apache-2.0
4
- base_model: hon9kon9ize/bert-base-cantonese
5
  tags:
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
9
  model-index:
10
- - name: bert-suicide-detection-hk-new
11
  results: []
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
- # bert-suicide-detection-hk-new
18
 
19
- This model is a fine-tuned version of [hon9kon9ize/bert-base-cantonese](https://huggingface.co/hon9kon9ize/bert-base-cantonese) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.3903
22
- - Accuracy: 0.9333
23
 
24
  ## Model description
25
 
@@ -44,93 +44,44 @@ The following hyperparameters were used during training:
44
  - seed: 42
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
- - num_epochs: 5
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|
53
- | 0.4227 | 0.0615 | 20 | 0.3869 | 0.8267 |
54
- | 0.4575 | 0.1231 | 40 | 0.2748 | 0.8733 |
55
- | 0.4332 | 0.1846 | 60 | 0.2883 | 0.84 |
56
- | 0.2946 | 0.2462 | 80 | 0.2482 | 0.8867 |
57
- | 0.2335 | 0.3077 | 100 | 0.2182 | 0.8933 |
58
- | 0.2751 | 0.3692 | 120 | 0.2767 | 0.9 |
59
- | 0.327 | 0.4308 | 140 | 0.6645 | 0.8067 |
60
- | 0.2839 | 0.4923 | 160 | 0.2197 | 0.9333 |
61
- | 0.2436 | 0.5538 | 180 | 0.2382 | 0.9267 |
62
- | 0.2855 | 0.6154 | 200 | 0.4087 | 0.88 |
63
- | 0.3372 | 0.6769 | 220 | 0.2596 | 0.94 |
64
- | 0.1343 | 0.7385 | 240 | 0.7997 | 0.84 |
65
- | 0.285 | 0.8 | 260 | 0.3252 | 0.9067 |
66
- | 0.145 | 0.8615 | 280 | 0.8378 | 0.8333 |
67
- | 0.2577 | 0.9231 | 300 | 0.4026 | 0.9067 |
68
- | 0.4514 | 0.9846 | 320 | 0.4263 | 0.8867 |
69
- | 0.245 | 1.0462 | 340 | 0.3208 | 0.9067 |
70
- | 0.0017 | 1.1077 | 360 | 0.5023 | 0.8733 |
71
- | 0.0176 | 1.1692 | 380 | 0.5177 | 0.88 |
72
- | 0.1223 | 1.2308 | 400 | 0.6029 | 0.88 |
73
- | 0.1639 | 1.2923 | 420 | 0.6401 | 0.88 |
74
- | 0.1752 | 1.3538 | 440 | 0.4151 | 0.9 |
75
- | 0.1417 | 1.4154 | 460 | 0.2314 | 0.9467 |
76
- | 0.1784 | 1.4769 | 480 | 0.4026 | 0.9133 |
77
- | 0.1671 | 1.5385 | 500 | 0.4188 | 0.9067 |
78
- | 0.2027 | 1.6 | 520 | 0.2420 | 0.94 |
79
- | 0.1009 | 1.6615 | 540 | 0.5572 | 0.86 |
80
- | 0.1411 | 1.7231 | 560 | 0.5484 | 0.8867 |
81
- | 0.078 | 1.7846 | 580 | 0.2864 | 0.9333 |
82
- | 0.2094 | 1.8462 | 600 | 0.4784 | 0.9067 |
83
- | 0.2487 | 1.9077 | 620 | 0.2854 | 0.9267 |
84
- | 0.1476 | 1.9692 | 640 | 0.2096 | 0.9467 |
85
- | 0.0111 | 2.0308 | 660 | 0.3278 | 0.9333 |
86
- | 0.056 | 2.0923 | 680 | 0.3028 | 0.94 |
87
- | 0.0025 | 2.1538 | 700 | 0.4313 | 0.9 |
88
- | 0.0171 | 2.2154 | 720 | 0.3401 | 0.9333 |
89
- | 0.2359 | 2.2769 | 740 | 0.3079 | 0.9467 |
90
- | 0.0966 | 2.3385 | 760 | 0.4836 | 0.9 |
91
- | 0.0375 | 2.4 | 780 | 0.5409 | 0.88 |
92
- | 0.1249 | 2.4615 | 800 | 0.2857 | 0.9467 |
93
- | 0.0408 | 2.5231 | 820 | 0.2854 | 0.94 |
94
- | 0.0685 | 2.5846 | 840 | 0.3301 | 0.94 |
95
- | 0.0676 | 2.6462 | 860 | 0.4170 | 0.9067 |
96
- | 0.09 | 2.7077 | 880 | 0.4455 | 0.9067 |
97
- | 0.0011 | 2.7692 | 900 | 0.3954 | 0.9267 |
98
- | 0.0198 | 2.8308 | 920 | 0.4213 | 0.9133 |
99
- | 0.1061 | 2.8923 | 940 | 0.3032 | 0.94 |
100
- | 0.0003 | 2.9538 | 960 | 0.3759 | 0.92 |
101
- | 0.0003 | 3.0154 | 980 | 0.3952 | 0.92 |
102
- | 0.0037 | 3.0769 | 1000 | 0.4295 | 0.9133 |
103
- | 0.0003 | 3.1385 | 1020 | 0.4906 | 0.9133 |
104
- | 0.0003 | 3.2 | 1040 | 0.4890 | 0.9133 |
105
- | 0.0642 | 3.2615 | 1060 | 0.3462 | 0.9333 |
106
- | 0.0003 | 3.3231 | 1080 | 0.3094 | 0.9467 |
107
- | 0.0003 | 3.3846 | 1100 | 0.3282 | 0.94 |
108
- | 0.1037 | 3.4462 | 1120 | 0.3809 | 0.9333 |
109
- | 0.0006 | 3.5077 | 1140 | 0.4448 | 0.9267 |
110
- | 0.0942 | 3.5692 | 1160 | 0.6031 | 0.8867 |
111
- | 0.0003 | 3.6308 | 1180 | 0.4964 | 0.8867 |
112
- | 0.0007 | 3.6923 | 1200 | 0.5269 | 0.8867 |
113
- | 0.0887 | 3.7538 | 1220 | 0.4914 | 0.8867 |
114
- | 0.0003 | 3.8154 | 1240 | 0.3959 | 0.9267 |
115
- | 0.0008 | 3.8769 | 1260 | 0.4240 | 0.9267 |
116
- | 0.0003 | 3.9385 | 1280 | 0.4334 | 0.92 |
117
- | 0.0003 | 4.0 | 1300 | 0.4242 | 0.9267 |
118
- | 0.0002 | 4.0615 | 1320 | 0.4218 | 0.9267 |
119
- | 0.0003 | 4.1231 | 1340 | 0.4187 | 0.9267 |
120
- | 0.0002 | 4.1846 | 1360 | 0.4103 | 0.9267 |
121
- | 0.0002 | 4.2462 | 1380 | 0.4091 | 0.9267 |
122
- | 0.0002 | 4.3077 | 1400 | 0.4111 | 0.9267 |
123
- | 0.0003 | 4.3692 | 1420 | 0.4092 | 0.9267 |
124
- | 0.0003 | 4.4308 | 1440 | 0.3991 | 0.9333 |
125
- | 0.0002 | 4.4923 | 1460 | 0.3991 | 0.9333 |
126
- | 0.0002 | 4.5538 | 1480 | 0.3986 | 0.9333 |
127
- | 0.0004 | 4.6154 | 1500 | 0.4055 | 0.9333 |
128
- | 0.1421 | 4.6769 | 1520 | 0.4006 | 0.9333 |
129
- | 0.0002 | 4.7385 | 1540 | 0.4030 | 0.9267 |
130
- | 0.0002 | 4.8 | 1560 | 0.4034 | 0.9267 |
131
- | 0.0628 | 4.8615 | 1580 | 0.3876 | 0.9333 |
132
- | 0.0003 | 4.9231 | 1600 | 0.3880 | 0.9333 |
133
- | 0.0003 | 4.9846 | 1620 | 0.3903 | 0.9333 |
134
 
135
 
136
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
+ license: cc-by-4.0
4
+ base_model: hon9kon9ize/bert-large-cantonese
5
  tags:
6
  - generated_from_trainer
7
  metrics:
8
  - accuracy
9
  model-index:
10
+ - name: bert-suicide-detection-hk-large-new
11
  results: []
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
  should probably proofread and complete it, then remove this comment. -->
16
 
17
+ # bert-suicide-detection-hk-large-new
18
 
19
+ This model is a fine-tuned version of [hon9kon9ize/bert-large-cantonese](https://huggingface.co/hon9kon9ize/bert-large-cantonese) on the None dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4360
22
+ - Accuracy: 0.8867
23
 
24
  ## Model description
25
 
 
44
  - seed: 42
45
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
+ - num_epochs: 2
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|
53
+ | 0.6486 | 0.0615 | 20 | 0.6136 | 0.82 |
54
+ | 0.5793 | 0.1231 | 40 | 0.8185 | 0.8067 |
55
+ | 0.7958 | 0.1846 | 60 | 0.4481 | 0.82 |
56
+ | 0.7368 | 0.2462 | 80 | 0.3714 | 0.82 |
57
+ | 0.4164 | 0.3077 | 100 | 0.6371 | 0.84 |
58
+ | 0.4822 | 0.3692 | 120 | 0.5196 | 0.82 |
59
+ | 0.4983 | 0.4308 | 140 | 1.0318 | 0.76 |
60
+ | 0.3606 | 0.4923 | 160 | 0.3952 | 0.8533 |
61
+ | 0.6422 | 0.5538 | 180 | 0.5667 | 0.8333 |
62
+ | 0.7958 | 0.6154 | 200 | 0.6493 | 0.8267 |
63
+ | 0.5221 | 0.6769 | 220 | 0.4448 | 0.8267 |
64
+ | 0.5065 | 0.7385 | 240 | 0.7102 | 0.8067 |
65
+ | 0.5758 | 0.8 | 260 | 0.5862 | 0.88 |
66
+ | 0.7866 | 0.8615 | 280 | 0.4026 | 0.88 |
67
+ | 0.2535 | 0.9231 | 300 | 0.4780 | 0.8733 |
68
+ | 0.649 | 0.9846 | 320 | 0.4977 | 0.8733 |
69
+ | 0.5498 | 1.0462 | 340 | 0.3915 | 0.8933 |
70
+ | 0.4721 | 1.1077 | 360 | 0.3703 | 0.9067 |
71
+ | 0.3445 | 1.1692 | 380 | 0.4002 | 0.8667 |
72
+ | 0.3252 | 1.2308 | 400 | 0.5739 | 0.86 |
73
+ | 0.2987 | 1.2923 | 420 | 0.6990 | 0.8533 |
74
+ | 0.3973 | 1.3538 | 440 | 0.5569 | 0.8533 |
75
+ | 0.3977 | 1.4154 | 460 | 0.4198 | 0.8867 |
76
+ | 0.3374 | 1.4769 | 480 | 0.4173 | 0.8733 |
77
+ | 0.3065 | 1.5385 | 500 | 0.5024 | 0.86 |
78
+ | 0.4698 | 1.6 | 520 | 0.4107 | 0.8933 |
79
+ | 0.2827 | 1.6615 | 540 | 0.5435 | 0.86 |
80
+ | 0.3331 | 1.7231 | 560 | 0.5321 | 0.8733 |
81
+ | 0.1841 | 1.7846 | 580 | 0.4208 | 0.8867 |
82
+ | 0.2626 | 1.8462 | 600 | 0.4387 | 0.8933 |
83
+ | 0.3547 | 1.9077 | 620 | 0.4360 | 0.8867 |
84
+ | 0.3534 | 1.9692 | 640 | 0.4360 | 0.8867 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85
 
86
 
87
  ### Framework versions