Hugging Face's logo

davidliu1110
/
bert-base-chinese-david-ner

Token Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
2
davidliu1110 commited on
Commit
3103232
•
1 Parent(s): 5ec528b

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -50
README.md CHANGED
@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.0588
22
- - Precision: 0.9447
23
- - Recall: 0.9479
24
- - F1: 0.9463
25
- - Accuracy: 0.9861
26
 
27
  ## Model description
28
 
@@ -54,51 +54,46 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
- | 0.9539 | 0.09 | 100 | 0.4089 | 0.2768 | 0.2401 | 0.2571 | 0.8587 |
58
- | 0.2552 | 0.18 | 200 | 0.1580 | 0.7110 | 0.7746 | 0.7415 | 0.9493 |
59
- | 0.1586 | 0.27 | 300 | 0.1327 | 0.7357 | 0.8448 | 0.7865 | 0.9569 |
60
- | 0.1322 | 0.35 | 400 | 0.1132 | 0.7820 | 0.8652 | 0.8215 | 0.9637 |
61
- | 0.1171 | 0.44 | 500 | 0.1135 | 0.8522 | 0.8618 | 0.8570 | 0.9681 |
62
- | 0.1 | 0.53 | 600 | 0.1008 | 0.8280 | 0.8720 | 0.8494 | 0.9685 |
63
- | 0.0925 | 0.62 | 700 | 0.0983 | 0.8519 | 0.8924 | 0.8717 | 0.9730 |
64
- | 0.0932 | 0.71 | 800 | 0.0720 | 0.8775 | 0.9003 | 0.8888 | 0.9771 |
65
- | 0.0846 | 0.8 | 900 | 0.0754 | 0.8879 | 0.9060 | 0.8969 | 0.9766 |
66
- | 0.0719 | 0.88 | 1000 | 0.0834 | 0.8713 | 0.8969 | 0.8839 | 0.9766 |
67
- | 0.0854 | 0.97 | 1100 | 0.0710 | 0.8970 | 0.9173 | 0.9071 | 0.9795 |
68
- | 0.0582 | 1.06 | 1200 | 0.0900 | 0.8760 | 0.8958 | 0.8858 | 0.9736 |
69
- | 0.0487 | 1.15 | 1300 | 0.0880 | 0.9027 | 0.9241 | 0.9133 | 0.9795 |
70
- | 0.0554 | 1.24 | 1400 | 0.0612 | 0.9132 | 0.9298 | 0.9214 | 0.9822 |
71
- | 0.0423 | 1.33 | 1500 | 0.0686 | 0.8958 | 0.9253 | 0.9103 | 0.9805 |
72
- | 0.0532 | 1.41 | 1600 | 0.0663 | 0.9070 | 0.9275 | 0.9171 | 0.9812 |
73
- | 0.0433 | 1.5 | 1700 | 0.0644 | 0.9270 | 0.9343 | 0.9306 | 0.9833 |
74
- | 0.0486 | 1.59 | 1800 | 0.0613 | 0.9099 | 0.9264 | 0.9181 | 0.9820 |
75
- | 0.0528 | 1.68 | 1900 | 0.0601 | 0.9201 | 0.9264 | 0.9233 | 0.9842 |
76
- | 0.0382 | 1.77 | 2000 | 0.0667 | 0.9172 | 0.9287 | 0.9229 | 0.9835 |
77
- | 0.0517 | 1.86 | 2100 | 0.0607 | 0.9260 | 0.9354 | 0.9307 | 0.9835 |
78
- | 0.0455 | 1.94 | 2200 | 0.0591 | 0.9147 | 0.9354 | 0.9250 | 0.9830 |
79
- | 0.0377 | 2.03 | 2300 | 0.0679 | 0.9238 | 0.9332 | 0.9285 | 0.9828 |
80
- | 0.0239 | 2.12 | 2400 | 0.0604 | 0.9246 | 0.9445 | 0.9345 | 0.9851 |
81
- | 0.0237 | 2.21 | 2500 | 0.0700 | 0.9233 | 0.9411 | 0.9321 | 0.9838 |
82
- | 0.0233 | 2.3 | 2600 | 0.0639 | 0.9201 | 0.9388 | 0.9294 | 0.9835 |
83
- | 0.0196 | 2.39 | 2700 | 0.0589 | 0.9352 | 0.9479 | 0.9415 | 0.9864 |
84
- | 0.0259 | 2.47 | 2800 | 0.0617 | 0.9337 | 0.9411 | 0.9374 | 0.9856 |
85
- | 0.0244 | 2.56 | 2900 | 0.0609 | 0.9379 | 0.9411 | 0.9395 | 0.9855 |
86
- | 0.0231 | 2.65 | 3000 | 0.0653 | 0.9383 | 0.9479 | 0.9431 | 0.9859 |
87
- | 0.0326 | 2.74 | 3100 | 0.0588 | 0.9447 | 0.9479 | 0.9463 | 0.9861 |
88
- | 0.0313 | 2.83 | 3200 | 0.0552 | 0.9446 | 0.9456 | 0.9451 | 0.9871 |
89
- | 0.0227 | 2.92 | 3300 | 0.0517 | 0.9394 | 0.9479 | 0.9436 | 0.9871 |
90
- | 0.0244 | 3.0 | 3400 | 0.0588 | 0.9259 | 0.9479 | 0.9368 | 0.9855 |
91
- | 0.0205 | 3.09 | 3500 | 0.0607 | 0.9224 | 0.9422 | 0.9322 | 0.9857 |
92
- | 0.0181 | 3.18 | 3600 | 0.0601 | 0.9266 | 0.9434 | 0.9349 | 0.9856 |
93
- | 0.0097 | 3.27 | 3700 | 0.0649 | 0.9360 | 0.9434 | 0.9397 | 0.9854 |
94
- | 0.0137 | 3.36 | 3800 | 0.0662 | 0.9372 | 0.9468 | 0.9420 | 0.9851 |
95
- | 0.0131 | 3.45 | 3900 | 0.0657 | 0.9353 | 0.9502 | 0.9427 | 0.9858 |
96
- | 0.0119 | 3.53 | 4000 | 0.0639 | 0.9373 | 0.9479 | 0.9426 | 0.9860 |
97
- | 0.0189 | 3.62 | 4100 | 0.0625 | 0.9371 | 0.9456 | 0.9414 | 0.9858 |
98
- | 0.0179 | 3.71 | 4200 | 0.0609 | 0.9385 | 0.9502 | 0.9443 | 0.9860 |
99
- | 0.0111 | 3.8 | 4300 | 0.0609 | 0.9362 | 0.9479 | 0.9420 | 0.9864 |
100
- | 0.0102 | 3.89 | 4400 | 0.0607 | 0.9383 | 0.9479 | 0.9431 | 0.9860 |
101
- | 0.0166 | 3.98 | 4500 | 0.0606 | 0.9395 | 0.9490 | 0.9442 | 0.9859 |
102
 
103
 
104
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0427
22
+ - Precision: 0.9485
23
+ - Recall: 0.9593
24
+ - F1: 0.9539
25
+ - Accuracy: 0.9908
26
 
27
  ## Model description
28
 
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
+ | 1.0343 | 0.1 | 100 | 0.4009 | 0.3314 | 0.2922 | 0.3106 | 0.8495 |
58
+ | 0.2482 | 0.2 | 200 | 0.1478 | 0.7218 | 0.7878 | 0.7533 | 0.9524 |
59
+ | 0.1598 | 0.3 | 300 | 0.1212 | 0.7666 | 0.8386 | 0.8010 | 0.9585 |
60
+ | 0.1266 | 0.39 | 400 | 0.1038 | 0.7890 | 0.8602 | 0.8231 | 0.9680 |
61
+ | 0.1092 | 0.49 | 500 | 0.0863 | 0.8298 | 0.8856 | 0.8568 | 0.9733 |
62
+ | 0.0978 | 0.59 | 600 | 0.0912 | 0.8575 | 0.9022 | 0.8793 | 0.9730 |
63
+ | 0.1001 | 0.69 | 700 | 0.0675 | 0.8867 | 0.9047 | 0.8956 | 0.9802 |
64
+ | 0.09 | 0.79 | 800 | 0.0635 | 0.8993 | 0.9187 | 0.9089 | 0.9825 |
65
+ | 0.0817 | 0.89 | 900 | 0.0679 | 0.8849 | 0.9187 | 0.9015 | 0.9791 |
66
+ | 0.0786 | 0.99 | 1000 | 0.0572 | 0.8936 | 0.9288 | 0.9109 | 0.9829 |
67
+ | 0.0553 | 1.09 | 1100 | 0.0752 | 0.9 | 0.9263 | 0.9130 | 0.9802 |
68
+ | 0.0591 | 1.18 | 1200 | 0.0572 | 0.9059 | 0.9301 | 0.9179 | 0.9849 |
69
+ | 0.0382 | 1.28 | 1300 | 0.0598 | 0.9180 | 0.9390 | 0.9284 | 0.9864 |
70
+ | 0.0543 | 1.38 | 1400 | 0.0530 | 0.9274 | 0.9416 | 0.9344 | 0.9874 |
71
+ | 0.0519 | 1.48 | 1500 | 0.0558 | 0.9106 | 0.9314 | 0.9209 | 0.9854 |
72
+ | 0.0504 | 1.58 | 1600 | 0.0692 | 0.9100 | 0.9377 | 0.9237 | 0.9825 |
73
+ | 0.0426 | 1.68 | 1700 | 0.0535 | 0.9203 | 0.9390 | 0.9296 | 0.9865 |
74
+ | 0.0455 | 1.78 | 1800 | 0.0503 | 0.9313 | 0.9479 | 0.9395 | 0.9882 |
75
+ | 0.0477 | 1.88 | 1900 | 0.0446 | 0.9293 | 0.9517 | 0.9404 | 0.9883 |
76
+ | 0.0402 | 1.97 | 2000 | 0.0384 | 0.9437 | 0.9593 | 0.9515 | 0.9907 |
77
+ | 0.0342 | 2.07 | 2100 | 0.0462 | 0.9257 | 0.9492 | 0.9373 | 0.9887 |
78
+ | 0.021 | 2.17 | 2200 | 0.0546 | 0.9337 | 0.9492 | 0.9414 | 0.9882 |
79
+ | 0.0289 | 2.27 | 2300 | 0.0434 | 0.9424 | 0.9555 | 0.9489 | 0.9908 |
80
+ | 0.027 | 2.37 | 2400 | 0.0434 | 0.9353 | 0.9555 | 0.9453 | 0.9891 |
81
+ | 0.0231 | 2.47 | 2500 | 0.0427 | 0.9485 | 0.9593 | 0.9539 | 0.9908 |
82
+ | 0.0229 | 2.57 | 2600 | 0.0447 | 0.9352 | 0.9530 | 0.9440 | 0.9893 |
83
+ | 0.0251 | 2.67 | 2700 | 0.0448 | 0.9485 | 0.9593 | 0.9539 | 0.9900 |
84
+ | 0.0284 | 2.76 | 2800 | 0.0463 | 0.9423 | 0.9543 | 0.9482 | 0.9899 |
85
+ | 0.0244 | 2.86 | 2900 | 0.0449 | 0.9411 | 0.9543 | 0.9476 | 0.9893 |
86
+ | 0.0233 | 2.96 | 3000 | 0.0461 | 0.9411 | 0.9543 | 0.9476 | 0.9888 |
87
+ | 0.0148 | 3.06 | 3100 | 0.0461 | 0.9401 | 0.9581 | 0.9490 | 0.9900 |
88
+ | 0.0153 | 3.16 | 3200 | 0.0460 | 0.9388 | 0.9555 | 0.9471 | 0.9900 |
89
+ | 0.0147 | 3.26 | 3300 | 0.0466 | 0.9374 | 0.9517 | 0.9445 | 0.9894 |
90
+ | 0.0133 | 3.36 | 3400 | 0.0467 | 0.9385 | 0.9504 | 0.9444 | 0.9891 |
91
+ | 0.0217 | 3.46 | 3500 | 0.0457 | 0.9301 | 0.9466 | 0.9383 | 0.9892 |
92
+ | 0.0143 | 3.55 | 3600 | 0.0451 | 0.9363 | 0.9530 | 0.9446 | 0.9900 |
93
+ | 0.0077 | 3.65 | 3700 | 0.0466 | 0.9401 | 0.9568 | 0.9484 | 0.9906 |
94
+ | 0.0138 | 3.75 | 3800 | 0.0482 | 0.9401 | 0.9568 | 0.9484 | 0.9908 |
95
+ | 0.0168 | 3.85 | 3900 | 0.0486 | 0.9387 | 0.9543 | 0.9464 | 0.9894 |
96
+ | 0.0195 | 3.95 | 4000 | 0.0471 | 0.9387 | 0.9543 | 0.9464 | 0.9900 |
 
 
 
 
 
97
 
98
 
99
  ### Framework versions