Hugging Face's logo

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

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
wcyat commited on
Commit
0bde1d7
·
verified ·
1 Parent(s): 67bed29

Model save

Browse files
Files changed (1) hide show
  1. README.md +93 -88
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: 0.4945
22
- - Accuracy: 0.9085
23
 
24
  ## Model description
25
 
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
42
  - train_batch_size: 4
43
  - eval_batch_size: 4
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
 
@@ -50,93 +50,98 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|
53
- | 0.5426 | 0.0604 | 20 | 0.7869 | 0.7451 |
54
- | 0.5984 | 0.1208 | 40 | 0.3943 | 0.7908 |
55
- | 0.4864 | 0.1813 | 60 | 0.9365 | 0.7843 |
56
- | 0.6039 | 0.2417 | 80 | 0.6580 | 0.7712 |
57
- | 0.5741 | 0.3021 | 100 | 0.3454 | 0.8235 |
58
- | 0.4276 | 0.3625 | 120 | 0.5421 | 0.8170 |
59
- | 0.4342 | 0.4230 | 140 | 0.4258 | 0.8562 |
60
- | 0.4915 | 0.4834 | 160 | 0.5961 | 0.8301 |
61
- | 0.4127 | 0.5438 | 180 | 0.2987 | 0.8693 |
62
- | 0.3166 | 0.6042 | 200 | 0.3308 | 0.8693 |
63
- | 0.4018 | 0.6647 | 220 | 0.5286 | 0.8039 |
64
- | 0.3007 | 0.7251 | 240 | 0.5845 | 0.8627 |
65
- | 0.4893 | 0.7855 | 260 | 0.3662 | 0.8627 |
66
- | 0.274 | 0.8459 | 280 | 0.3483 | 0.8693 |
67
- | 0.5741 | 0.9063 | 300 | 0.3280 | 0.8824 |
68
- | 0.3752 | 0.9668 | 320 | 0.5251 | 0.8889 |
69
- | 0.2711 | 1.0272 | 340 | 0.6097 | 0.8562 |
70
- | 0.2369 | 1.0876 | 360 | 0.5457 | 0.8693 |
71
- | 0.3756 | 1.1480 | 380 | 0.6890 | 0.8758 |
72
- | 0.6575 | 1.2085 | 400 | 0.4709 | 0.8693 |
73
- | 0.3268 | 1.2689 | 420 | 0.5219 | 0.8497 |
74
- | 0.3994 | 1.3293 | 440 | 0.4282 | 0.8693 |
75
- | 0.0879 | 1.3897 | 460 | 0.6294 | 0.8758 |
76
- | 0.2566 | 1.4502 | 480 | 0.7143 | 0.8627 |
77
- | 0.2897 | 1.5106 | 500 | 0.6120 | 0.8693 |
78
- | 0.321 | 1.5710 | 520 | 0.4749 | 0.8758 |
79
- | 0.1871 | 1.6314 | 540 | 0.4392 | 0.9085 |
80
- | 0.1654 | 1.6918 | 560 | 0.4663 | 0.9085 |
81
- | 0.3166 | 1.7523 | 580 | 0.5048 | 0.8889 |
82
- | 0.222 | 1.8127 | 600 | 0.4550 | 0.9085 |
83
- | 0.4299 | 1.8731 | 620 | 0.3445 | 0.9085 |
84
- | 0.0942 | 1.9335 | 640 | 0.3735 | 0.9281 |
85
- | 0.3991 | 1.9940 | 660 | 0.3646 | 0.9085 |
86
- | 0.0581 | 2.0544 | 680 | 0.3527 | 0.9085 |
87
- | 0.2712 | 2.1148 | 700 | 0.4270 | 0.9020 |
88
- | 0.0443 | 2.1752 | 720 | 0.5462 | 0.8954 |
89
- | 0.3831 | 2.2356 | 740 | 0.3419 | 0.9216 |
90
- | 0.2267 | 2.2961 | 760 | 0.4925 | 0.8889 |
91
- | 0.1821 | 2.3565 | 780 | 0.3625 | 0.9216 |
92
- | 0.2926 | 2.4169 | 800 | 0.3671 | 0.9020 |
93
- | 0.2507 | 2.4773 | 820 | 0.3853 | 0.9020 |
94
- | 0.2446 | 2.5378 | 840 | 0.4571 | 0.8954 |
95
- | 0.1926 | 2.5982 | 860 | 0.5436 | 0.8497 |
96
- | 0.1725 | 2.6586 | 880 | 0.6576 | 0.8497 |
97
- | 0.2033 | 2.7190 | 900 | 0.4772 | 0.9020 |
98
- | 0.0095 | 2.7795 | 920 | 0.4103 | 0.9150 |
99
- | 0.2896 | 2.8399 | 940 | 0.4333 | 0.9085 |
100
- | 0.2661 | 2.9003 | 960 | 0.5793 | 0.8889 |
101
- | 0.1338 | 2.9607 | 980 | 0.4543 | 0.8954 |
102
- | 0.0751 | 3.0211 | 1000 | 0.5029 | 0.8954 |
103
- | 0.2093 | 3.0816 | 1020 | 0.4631 | 0.9020 |
104
- | 0.2436 | 3.1420 | 1040 | 0.5888 | 0.8693 |
105
- | 0.1375 | 3.2024 | 1060 | 0.6457 | 0.8889 |
106
- | 0.0049 | 3.2628 | 1080 | 0.6601 | 0.8889 |
107
- | 0.0089 | 3.3233 | 1100 | 0.6462 | 0.8824 |
108
- | 0.0616 | 3.3837 | 1120 | 0.6607 | 0.8889 |
109
- | 0.006 | 3.4441 | 1140 | 0.6243 | 0.9020 |
110
- | 0.1769 | 3.5045 | 1160 | 0.5257 | 0.9020 |
111
- | 0.0044 | 3.5650 | 1180 | 0.5508 | 0.9085 |
112
- | 0.2295 | 3.6254 | 1200 | 0.4846 | 0.9150 |
113
- | 0.1175 | 3.6858 | 1220 | 0.4764 | 0.9020 |
114
- | 0.0746 | 3.7462 | 1240 | 0.4761 | 0.9020 |
115
- | 0.0222 | 3.8066 | 1260 | 0.4836 | 0.9020 |
116
- | 0.0012 | 3.8671 | 1280 | 0.4775 | 0.9216 |
117
- | 0.2131 | 3.9275 | 1300 | 0.4607 | 0.9020 |
118
- | 0.0006 | 3.9879 | 1320 | 0.4935 | 0.9085 |
119
- | 0.0758 | 4.0483 | 1340 | 0.4592 | 0.9020 |
120
- | 0.1466 | 4.1088 | 1360 | 0.4464 | 0.9085 |
121
- | 0.0488 | 4.1692 | 1380 | 0.4816 | 0.9085 |
122
- | 0.0014 | 4.2296 | 1400 | 0.4570 | 0.9150 |
123
- | 0.082 | 4.2900 | 1420 | 0.4545 | 0.9216 |
124
- | 0.0009 | 4.3505 | 1440 | 0.4721 | 0.9150 |
125
- | 0.0008 | 4.4109 | 1460 | 0.4874 | 0.9216 |
126
- | 0.0014 | 4.4713 | 1480 | 0.5003 | 0.9150 |
127
- | 0.1612 | 4.5317 | 1500 | 0.5064 | 0.9150 |
128
- | 0.2079 | 4.5921 | 1520 | 0.4994 | 0.9150 |
129
- | 0.1423 | 4.6526 | 1540 | 0.4835 | 0.9150 |
130
- | 0.0009 | 4.7130 | 1560 | 0.4825 | 0.9085 |
131
- | 0.0017 | 4.7734 | 1580 | 0.4918 | 0.9085 |
132
- | 0.0648 | 4.8338 | 1600 | 0.4917 | 0.9150 |
133
- | 0.0531 | 4.8943 | 1620 | 0.4919 | 0.9085 |
134
- | 0.0008 | 4.9547 | 1640 | 0.4945 | 0.9085 |
 
 
 
 
 
135
 
136
 
137
  ### Framework versions
138
 
139
- - Transformers 4.47.1
140
- - Pytorch 2.5.1+cu121
141
- - Datasets 3.2.0
142
  - Tokenizers 0.21.0
 
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: 0.5925
22
+ - Accuracy: 0.8987
23
 
24
  ## Model description
25
 
 
42
  - train_batch_size: 4
43
  - eval_batch_size: 4
44
  - seed: 42
45
+ - optimizer: Use OptimizerNames.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
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:------:|:----:|:---------------:|:--------:|
53
+ | 0.5908 | 0.0573 | 20 | 0.4476 | 0.7975 |
54
+ | 0.543 | 0.1146 | 40 | 0.4423 | 0.7722 |
55
+ | 0.5093 | 0.1719 | 60 | 0.5882 | 0.7722 |
56
+ | 0.5186 | 0.2292 | 80 | 0.6422 | 0.7658 |
57
+ | 0.502 | 0.2865 | 100 | 0.9382 | 0.7658 |
58
+ | 0.573 | 0.3438 | 120 | 0.4264 | 0.8228 |
59
+ | 0.5269 | 0.4011 | 140 | 0.5453 | 0.8481 |
60
+ | 0.3545 | 0.4585 | 160 | 0.4541 | 0.8924 |
61
+ | 0.4449 | 0.5158 | 180 | 0.4354 | 0.8924 |
62
+ | 0.3868 | 0.5731 | 200 | 0.8784 | 0.8481 |
63
+ | 0.7576 | 0.6304 | 220 | 0.3822 | 0.8861 |
64
+ | 0.1956 | 0.6877 | 240 | 0.4668 | 0.8797 |
65
+ | 0.4942 | 0.7450 | 260 | 0.5736 | 0.8481 |
66
+ | 0.4762 | 0.8023 | 280 | 0.2911 | 0.8987 |
67
+ | 0.4136 | 0.8596 | 300 | 0.3629 | 0.8608 |
68
+ | 0.5865 | 0.9169 | 320 | 0.9794 | 0.7722 |
69
+ | 0.3758 | 0.9742 | 340 | 0.4678 | 0.8734 |
70
+ | 0.4285 | 1.0315 | 360 | 0.5543 | 0.8671 |
71
+ | 0.44 | 1.0888 | 380 | 0.5150 | 0.8608 |
72
+ | 0.3573 | 1.1461 | 400 | 0.5635 | 0.8608 |
73
+ | 0.4187 | 1.2034 | 420 | 0.6609 | 0.8481 |
74
+ | 0.3742 | 1.2607 | 440 | 0.5913 | 0.8481 |
75
+ | 0.5179 | 1.3181 | 460 | 0.3984 | 0.8354 |
76
+ | 0.1685 | 1.3754 | 480 | 0.5607 | 0.8734 |
77
+ | 0.5284 | 1.4327 | 500 | 0.3528 | 0.8924 |
78
+ | 0.4246 | 1.4900 | 520 | 0.5857 | 0.8608 |
79
+ | 0.2419 | 1.5473 | 540 | 0.3496 | 0.9051 |
80
+ | 0.4416 | 1.6046 | 560 | 0.4946 | 0.8861 |
81
+ | 0.4426 | 1.6619 | 580 | 0.3458 | 0.9051 |
82
+ | 0.2122 | 1.7192 | 600 | 0.6184 | 0.8987 |
83
+ | 0.1734 | 1.7765 | 620 | 0.7278 | 0.8734 |
84
+ | 0.2314 | 1.8338 | 640 | 0.5430 | 0.8861 |
85
+ | 0.4886 | 1.8911 | 660 | 0.5081 | 0.8861 |
86
+ | 0.3429 | 1.9484 | 680 | 0.6000 | 0.8481 |
87
+ | 0.3591 | 2.0057 | 700 | 0.5184 | 0.8608 |
88
+ | 0.3638 | 2.0630 | 720 | 0.4008 | 0.8861 |
89
+ | 0.1881 | 2.1203 | 740 | 0.6161 | 0.8734 |
90
+ | 0.241 | 2.1777 | 760 | 0.5249 | 0.8861 |
91
+ | 0.4699 | 2.2350 | 780 | 0.5323 | 0.8861 |
92
+ | 0.3702 | 2.2923 | 800 | 0.7284 | 0.8481 |
93
+ | 0.4192 | 2.3496 | 820 | 0.3671 | 0.9051 |
94
+ | 0.1747 | 2.4069 | 840 | 0.4293 | 0.9051 |
95
+ | 0.347 | 2.4642 | 860 | 0.4047 | 0.8924 |
96
+ | 0.0533 | 2.5215 | 880 | 0.5135 | 0.8861 |
97
+ | 0.2002 | 2.5788 | 900 | 0.5535 | 0.8797 |
98
+ | 0.0274 | 2.6361 | 920 | 0.6635 | 0.8734 |
99
+ | 0.2339 | 2.6934 | 940 | 0.4940 | 0.8924 |
100
+ | 0.3015 | 2.7507 | 960 | 0.5514 | 0.8734 |
101
+ | 0.4222 | 2.8080 | 980 | 0.5412 | 0.8734 |
102
+ | 0.3243 | 2.8653 | 1000 | 0.5440 | 0.8734 |
103
+ | 0.3137 | 2.9226 | 1020 | 0.4534 | 0.8861 |
104
+ | 0.191 | 2.9799 | 1040 | 0.6083 | 0.8797 |
105
+ | 0.1213 | 3.0372 | 1060 | 0.5798 | 0.8734 |
106
+ | 0.1582 | 3.0946 | 1080 | 0.4830 | 0.8861 |
107
+ | 0.0546 | 3.1519 | 1100 | 0.7039 | 0.8734 |
108
+ | 0.0387 | 3.2092 | 1120 | 0.6059 | 0.8924 |
109
+ | 0.4619 | 3.2665 | 1140 | 0.6934 | 0.8861 |
110
+ | 0.2789 | 3.3238 | 1160 | 0.5247 | 0.9051 |
111
+ | 0.1361 | 3.3811 | 1180 | 0.6307 | 0.8797 |
112
+ | 0.0475 | 3.4384 | 1200 | 0.5455 | 0.8924 |
113
+ | 0.2889 | 3.4957 | 1220 | 0.5865 | 0.8797 |
114
+ | 0.2507 | 3.5530 | 1240 | 0.5029 | 0.8861 |
115
+ | 0.1476 | 3.6103 | 1260 | 0.6517 | 0.8797 |
116
+ | 0.0709 | 3.6676 | 1280 | 0.5607 | 0.8797 |
117
+ | 0.2416 | 3.7249 | 1300 | 0.6906 | 0.8671 |
118
+ | 0.2482 | 3.7822 | 1320 | 0.4523 | 0.8987 |
119
+ | 0.1591 | 3.8395 | 1340 | 0.3677 | 0.9177 |
120
+ | 0.1728 | 3.8968 | 1360 | 0.4237 | 0.9051 |
121
+ | 0.1061 | 3.9542 | 1380 | 0.3708 | 0.9241 |
122
+ | 0.1461 | 4.0115 | 1400 | 0.4642 | 0.9051 |
123
+ | 0.0671 | 4.0688 | 1420 | 0.5567 | 0.8924 |
124
+ | 0.0363 | 4.1261 | 1440 | 0.6240 | 0.8861 |
125
+ | 0.1257 | 4.1834 | 1460 | 0.7054 | 0.8734 |
126
+ | 0.1307 | 4.2407 | 1480 | 0.6526 | 0.8861 |
127
+ | 0.226 | 4.2980 | 1500 | 0.5883 | 0.8797 |
128
+ | 0.0714 | 4.3553 | 1520 | 0.5382 | 0.8987 |
129
+ | 0.0617 | 4.4126 | 1540 | 0.6030 | 0.8924 |
130
+ | 0.0802 | 4.4699 | 1560 | 0.5677 | 0.8924 |
131
+ | 0.2404 | 4.5272 | 1580 | 0.5837 | 0.8987 |
132
+ | 0.2311 | 4.5845 | 1600 | 0.6192 | 0.8987 |
133
+ | 0.0031 | 4.6418 | 1620 | 0.6153 | 0.8987 |
134
+ | 0.1621 | 4.6991 | 1640 | 0.6008 | 0.8924 |
135
+ | 0.0841 | 4.7564 | 1660 | 0.5887 | 0.8987 |
136
+ | 0.0014 | 4.8138 | 1680 | 0.5866 | 0.8987 |
137
+ | 0.1199 | 4.8711 | 1700 | 0.5909 | 0.8987 |
138
+ | 0.0124 | 4.9284 | 1720 | 0.5906 | 0.8987 |
139
+ | 0.046 | 4.9857 | 1740 | 0.5925 | 0.8987 |
140
 
141
 
142
  ### Framework versions
143
 
144
+ - Transformers 4.48.3
145
+ - Pytorch 2.5.1+cu124
146
+ - Datasets 3.3.2
147
  - Tokenizers 0.21.0