Hugging Face's logo

luohuashijieyoufengjun
/
ner_based_bert-base-chinese_badcase1

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
luohuashijieyoufengjun commited on
Commit
d86f2ed
·
verified ·
1 Parent(s): 8a231cf

End of training

Browse files
Files changed (3) hide show
  1. README.md +14 -14
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -21,10 +21,10 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [google-bert/bert-base-chinese](https://huggingface.co/google-bert/bert-base-chinese) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.0149
25
- - Precision: 0.9527
26
- - Recall: 0.9611
27
- - F1: 0.9569
28
  - Accuracy: 0.9967
29
 
30
  ## Model description
@@ -58,16 +58,16 @@ The following hyperparameters were used during training:
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
60
  |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
61
- | 0.1432 | 1.0 | 652 | 0.0278 | 0.8708 | 0.9159 | 0.8928 | 0.9916 |
62
- | 0.0267 | 2.0 | 1304 | 0.0203 | 0.9055 | 0.9351 | 0.9200 | 0.9942 |
63
- | 0.0206 | 3.0 | 1956 | 0.0191 | 0.9106 | 0.9450 | 0.9274 | 0.9945 |
64
- | 0.0137 | 4.0 | 2608 | 0.0167 | 0.9295 | 0.9498 | 0.9396 | 0.9954 |
65
- | 0.012 | 5.0 | 3260 | 0.0156 | 0.9320 | 0.9518 | 0.9418 | 0.9957 |
66
- | 0.0105 | 6.0 | 3912 | 0.0140 | 0.9401 | 0.9560 | 0.9480 | 0.9962 |
67
- | 0.0075 | 7.0 | 4564 | 0.0143 | 0.9464 | 0.9533 | 0.9498 | 0.9963 |
68
- | 0.0066 | 8.0 | 5216 | 0.0151 | 0.9462 | 0.9599 | 0.9530 | 0.9964 |
69
- | 0.0058 | 9.0 | 5868 | 0.0147 | 0.9468 | 0.9583 | 0.9525 | 0.9965 |
70
- | 0.0045 | 9.9847 | 6510 | 0.0149 | 0.9527 | 0.9611 | 0.9569 | 0.9967 |
71
 
72
 
73
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [google-bert/bert-base-chinese](https://huggingface.co/google-bert/bert-base-chinese) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.0153
25
+ - Precision: 0.9528
26
+ - Recall: 0.9620
27
+ - F1: 0.9574
28
  - Accuracy: 0.9967
29
 
30
  ## Model description
 
58
 
59
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
60
  |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
61
+ | 0.1473 | 1.0 | 652 | 0.0276 | 0.8679 | 0.9207 | 0.8935 | 0.9919 |
62
+ | 0.0262 | 2.0 | 1304 | 0.0197 | 0.9051 | 0.9397 | 0.9221 | 0.9942 |
63
+ | 0.0203 | 3.0 | 1956 | 0.0208 | 0.9093 | 0.9381 | 0.9235 | 0.9941 |
64
+ | 0.0134 | 4.0 | 2608 | 0.0168 | 0.9193 | 0.9570 | 0.9378 | 0.9953 |
65
+ | 0.0118 | 5.0 | 3260 | 0.0153 | 0.9378 | 0.9559 | 0.9467 | 0.9960 |
66
+ | 0.0099 | 6.0 | 3912 | 0.0146 | 0.9420 | 0.9592 | 0.9505 | 0.9963 |
67
+ | 0.0073 | 7.0 | 4564 | 0.0159 | 0.9390 | 0.9621 | 0.9504 | 0.9962 |
68
+ | 0.0065 | 8.0 | 5216 | 0.0147 | 0.9449 | 0.9644 | 0.9546 | 0.9965 |
69
+ | 0.0056 | 9.0 | 5868 | 0.0145 | 0.9531 | 0.9607 | 0.9569 | 0.9967 |
70
+ | 0.0044 | 9.9847 | 6510 | 0.0153 | 0.9528 | 0.9620 | 0.9574 | 0.9967 |
71
 
72
 
73
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b40a9ab4d895b3deba47cf6ffc8b0b5350f073075cd02be4d9987c6348ad7f2b
3
  size 406799208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c7d988a1b0e8d7ea6af2b6d610eb4b66b3bc2e033c92ef78404315040faed0
3
  size 406799208
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bfd06f063ee125a6e91894ff01a6f6a4c9820bd861ac57392696a65bf6ab8419
3
  size 5777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f033a7d140111f2303515f5ddcf824bff79f34766dfc93ab3add8042442ebe8a
3
  size 5777