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
27e8c30
·
verified ·
1 Parent(s): 892c497

Model save

Browse files
Files changed (1) hide show
  1. README.md +84 -35
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.4643
22
- - Accuracy: 0.9133
23
 
24
  ## Model description
25
 
@@ -44,44 +44,93 @@ 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: 2
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|
53
- | 0.2065 | 0.0615 | 20 | 0.5962 | 0.8667 |
54
- | 0.3593 | 0.1231 | 40 | 0.3982 | 0.8933 |
55
- | 0.5221 | 0.1846 | 60 | 0.6080 | 0.86 |
56
- | 0.4848 | 0.2462 | 80 | 0.5127 | 0.88 |
57
- | 0.211 | 0.3077 | 100 | 0.3958 | 0.8933 |
58
- | 0.3221 | 0.3692 | 120 | 0.4329 | 0.8667 |
59
- | 0.2949 | 0.4308 | 140 | 0.6028 | 0.8467 |
60
- | 0.3181 | 0.4923 | 160 | 0.4687 | 0.8667 |
61
- | 0.4452 | 0.5538 | 180 | 0.5136 | 0.8867 |
62
- | 0.3928 | 0.6154 | 200 | 0.5390 | 0.8667 |
63
- | 0.3589 | 0.6769 | 220 | 0.3812 | 0.9133 |
64
- | 0.3083 | 0.7385 | 240 | 0.7053 | 0.8533 |
65
- | 0.424 | 0.8 | 260 | 0.6005 | 0.8733 |
66
- | 0.4478 | 0.8615 | 280 | 0.5868 | 0.86 |
67
- | 0.0968 | 0.9231 | 300 | 0.5174 | 0.8933 |
68
- | 0.5289 | 0.9846 | 320 | 0.6539 | 0.86 |
69
- | 0.2927 | 1.0462 | 340 | 0.4807 | 0.8933 |
70
- | 0.1856 | 1.1077 | 360 | 0.4719 | 0.9067 |
71
- | 0.2246 | 1.1692 | 380 | 0.6224 | 0.8733 |
72
- | 0.2616 | 1.2308 | 400 | 0.6501 | 0.8733 |
73
- | 0.1283 | 1.2923 | 420 | 0.7043 | 0.8733 |
74
- | 0.2356 | 1.3538 | 440 | 0.5646 | 0.8867 |
75
- | 0.2042 | 1.4154 | 460 | 0.4638 | 0.9067 |
76
- | 0.235 | 1.4769 | 480 | 0.5954 | 0.8733 |
77
- | 0.098 | 1.5385 | 500 | 0.5677 | 0.88 |
78
- | 0.3059 | 1.6 | 520 | 0.5472 | 0.8933 |
79
- | 0.083 | 1.6615 | 540 | 0.5192 | 0.8867 |
80
- | 0.2128 | 1.7231 | 560 | 0.5108 | 0.8867 |
81
- | 0.0938 | 1.7846 | 580 | 0.5156 | 0.8933 |
82
- | 0.2221 | 1.8462 | 600 | 0.5102 | 0.8933 |
83
- | 0.262 | 1.9077 | 620 | 0.4842 | 0.9067 |
84
- | 0.2606 | 1.9692 | 640 | 0.4643 | 0.9133 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85
 
86
 
87
  ### Framework versions
 
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: 0.2903
22
+ - Accuracy: 0.9467
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: 5
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|
53
+ | 0.6203 | 0.0613 | 20 | 0.4148 | 0.8267 |
54
+ | 0.3246 | 0.1227 | 40 | 0.8805 | 0.8 |
55
+ | 0.5453 | 0.1840 | 60 | 0.3735 | 0.8667 |
56
+ | 0.4513 | 0.2454 | 80 | 0.4391 | 0.8867 |
57
+ | 0.7729 | 0.3067 | 100 | 0.4407 | 0.82 |
58
+ | 0.5867 | 0.3681 | 120 | 0.4013 | 0.8467 |
59
+ | 0.4073 | 0.4294 | 140 | 0.5397 | 0.86 |
60
+ | 0.1883 | 0.4908 | 160 | 0.7620 | 0.8667 |
61
+ | 0.4166 | 0.5521 | 180 | 0.6517 | 0.8933 |
62
+ | 0.4672 | 0.6135 | 200 | 0.6163 | 0.88 |
63
+ | 0.6858 | 0.6748 | 220 | 0.3484 | 0.8667 |
64
+ | 0.335 | 0.7362 | 240 | 0.6031 | 0.8533 |
65
+ | 0.4525 | 0.7975 | 260 | 0.6941 | 0.82 |
66
+ | 0.2385 | 0.8589 | 280 | 0.5618 | 0.88 |
67
+ | 0.4256 | 0.9202 | 300 | 0.5899 | 0.88 |
68
+ | 0.4934 | 0.9816 | 320 | 0.3289 | 0.9 |
69
+ | 0.277 | 1.0429 | 340 | 0.5671 | 0.88 |
70
+ | 0.5097 | 1.1043 | 360 | 0.5247 | 0.88 |
71
+ | 0.105 | 1.1656 | 380 | 0.4810 | 0.9 |
72
+ | 0.3976 | 1.2270 | 400 | 0.4562 | 0.8933 |
73
+ | 0.3506 | 1.2883 | 420 | 0.3943 | 0.8867 |
74
+ | 0.2057 | 1.3497 | 440 | 0.4944 | 0.8933 |
75
+ | 0.2788 | 1.4110 | 460 | 0.4718 | 0.9 |
76
+ | 0.4049 | 1.4724 | 480 | 0.5067 | 0.88 |
77
+ | 0.415 | 1.5337 | 500 | 0.4395 | 0.9 |
78
+ | 0.3565 | 1.5951 | 520 | 0.3682 | 0.9 |
79
+ | 0.3111 | 1.6564 | 540 | 0.3298 | 0.9 |
80
+ | 0.4191 | 1.7178 | 560 | 0.4493 | 0.8733 |
81
+ | 0.2731 | 1.7791 | 580 | 0.3832 | 0.9067 |
82
+ | 0.1803 | 1.8405 | 600 | 0.4403 | 0.8933 |
83
+ | 0.4462 | 1.9018 | 620 | 0.3844 | 0.9067 |
84
+ | 0.0025 | 1.9632 | 640 | 0.4563 | 0.9067 |
85
+ | 0.1574 | 2.0245 | 660 | 0.5508 | 0.8933 |
86
+ | 0.0927 | 2.0859 | 680 | 0.5529 | 0.9067 |
87
+ | 0.184 | 2.1472 | 700 | 0.5161 | 0.9 |
88
+ | 0.2446 | 2.2086 | 720 | 0.5064 | 0.8933 |
89
+ | 0.2498 | 2.2699 | 740 | 0.4034 | 0.92 |
90
+ | 0.2217 | 2.3313 | 760 | 0.5095 | 0.8733 |
91
+ | 0.2938 | 2.3926 | 780 | 0.3754 | 0.9067 |
92
+ | 0.109 | 2.4540 | 800 | 0.4771 | 0.8933 |
93
+ | 0.0282 | 2.5153 | 820 | 0.5535 | 0.8933 |
94
+ | 0.2455 | 2.5767 | 840 | 0.4206 | 0.9067 |
95
+ | 0.4728 | 2.6380 | 860 | 0.3018 | 0.9067 |
96
+ | 0.1145 | 2.6994 | 880 | 0.3053 | 0.9067 |
97
+ | 0.1045 | 2.7607 | 900 | 0.3431 | 0.9067 |
98
+ | 0.2207 | 2.8221 | 920 | 0.6482 | 0.86 |
99
+ | 0.427 | 2.8834 | 940 | 0.4396 | 0.9133 |
100
+ | 0.1898 | 2.9448 | 960 | 0.3327 | 0.92 |
101
+ | 0.0019 | 3.0061 | 980 | 0.3993 | 0.92 |
102
+ | 0.0842 | 3.0675 | 1000 | 0.4166 | 0.9267 |
103
+ | 0.1619 | 3.1288 | 1020 | 0.4181 | 0.9133 |
104
+ | 0.1849 | 3.1902 | 1040 | 0.4727 | 0.92 |
105
+ | 0.1949 | 3.2515 | 1060 | 0.3346 | 0.8933 |
106
+ | 0.1796 | 3.3129 | 1080 | 0.3471 | 0.9267 |
107
+ | 0.086 | 3.3742 | 1100 | 0.4089 | 0.8867 |
108
+ | 0.0187 | 3.4356 | 1120 | 0.3868 | 0.92 |
109
+ | 0.0768 | 3.4969 | 1140 | 0.4095 | 0.9267 |
110
+ | 0.0008 | 3.5583 | 1160 | 0.3780 | 0.9067 |
111
+ | 0.183 | 3.6196 | 1180 | 0.3827 | 0.9 |
112
+ | 0.204 | 3.6810 | 1200 | 0.5133 | 0.9 |
113
+ | 0.0758 | 3.7423 | 1220 | 0.4280 | 0.9133 |
114
+ | 0.0237 | 3.8037 | 1240 | 0.3942 | 0.92 |
115
+ | 0.2143 | 3.8650 | 1260 | 0.3680 | 0.9067 |
116
+ | 0.0106 | 3.9264 | 1280 | 0.5633 | 0.8867 |
117
+ | 0.2221 | 3.9877 | 1300 | 0.3815 | 0.92 |
118
+ | 0.0212 | 4.0491 | 1320 | 0.4599 | 0.9267 |
119
+ | 0.1678 | 4.1104 | 1340 | 0.3458 | 0.92 |
120
+ | 0.1153 | 4.1718 | 1360 | 0.3261 | 0.92 |
121
+ | 0.0006 | 4.2331 | 1380 | 0.3404 | 0.9133 |
122
+ | 0.0193 | 4.2945 | 1400 | 0.3602 | 0.92 |
123
+ | 0.0994 | 4.3558 | 1420 | 0.3303 | 0.94 |
124
+ | 0.0032 | 4.4172 | 1440 | 0.2885 | 0.94 |
125
+ | 0.0008 | 4.4785 | 1460 | 0.3112 | 0.92 |
126
+ | 0.0823 | 4.5399 | 1480 | 0.3145 | 0.9267 |
127
+ | 0.0086 | 4.6012 | 1500 | 0.2954 | 0.94 |
128
+ | 0.0009 | 4.6626 | 1520 | 0.3082 | 0.94 |
129
+ | 0.1619 | 4.7239 | 1540 | 0.2928 | 0.94 |
130
+ | 0.0004 | 4.7853 | 1560 | 0.2909 | 0.9333 |
131
+ | 0.0006 | 4.8466 | 1580 | 0.2879 | 0.9467 |
132
+ | 0.0005 | 4.9080 | 1600 | 0.2894 | 0.9467 |
133
+ | 0.0559 | 4.9693 | 1620 | 0.2903 | 0.9467 |
134
 
135
 
136
  ### Framework versions