Hugging Face's logo

luohuashijieyoufengjun
/
ner_based_bert-base-chinese

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
luohuashijieyoufengjun commited on
Commit
c04138a
·
verified ·
1 Parent(s): 00a4c6b

End of training

Browse files
Files changed (4) hide show
  1. README.md +13 -69
  2. model.safetensors +1 -1
  3. tokenizer.json +1 -1
  4. training_args.bin +1 -1
README.md CHANGED
@@ -3,11 +3,6 @@ library_name: transformers
3
  base_model: google-bert/bert-base-chinese
4
  tags:
5
  - generated_from_trainer
6
- metrics:
7
- - precision
8
- - recall
9
- - f1
10
- - accuracy
11
  model-index:
12
  - name: ner_based_bert-base-chinese
13
  results: []
@@ -20,11 +15,16 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  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.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0429
24
- - Precision: 0.9487
25
- - Recall: 0.9514
26
- - F1: 0.9501
27
- - Accuracy: 0.9957
 
 
 
 
 
28
 
29
  ## Model description
30
 
@@ -44,70 +44,14 @@ More information needed
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 2e-05
47
- - train_batch_size: 16
48
- - eval_batch_size: 16
49
  - seed: 42
50
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: linear
52
- - num_epochs: 50
53
  - mixed_precision_training: Native AMP
54
 
55
- ### Training results
56
-
57
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
- |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
- | 0.0294 | 1.0 | 1981 | 0.0255 | 0.8782 | 0.9345 | 0.9055 | 0.9923 |
60
- | 0.0169 | 2.0 | 3962 | 0.0214 | 0.9167 | 0.9362 | 0.9263 | 0.9942 |
61
- | 0.0113 | 3.0 | 5943 | 0.0213 | 0.9206 | 0.9464 | 0.9333 | 0.9948 |
62
- | 0.0069 | 4.0 | 7924 | 0.0228 | 0.9224 | 0.9518 | 0.9369 | 0.9949 |
63
- | 0.0044 | 5.0 | 9905 | 0.0228 | 0.9267 | 0.9432 | 0.9349 | 0.9950 |
64
- | 0.0039 | 6.0 | 11886 | 0.0255 | 0.9323 | 0.9416 | 0.9369 | 0.9949 |
65
- | 0.0024 | 7.0 | 13867 | 0.0300 | 0.9385 | 0.9443 | 0.9414 | 0.9951 |
66
- | 0.0028 | 8.0 | 15848 | 0.0276 | 0.9323 | 0.9491 | 0.9407 | 0.9952 |
67
- | 0.0022 | 9.0 | 17829 | 0.0297 | 0.9371 | 0.9459 | 0.9415 | 0.9952 |
68
- | 0.0019 | 10.0 | 19810 | 0.0306 | 0.9318 | 0.9479 | 0.9397 | 0.9950 |
69
- | 0.0012 | 11.0 | 21791 | 0.0326 | 0.9298 | 0.9500 | 0.9398 | 0.9951 |
70
- | 0.0016 | 12.0 | 23772 | 0.0344 | 0.9329 | 0.9496 | 0.9412 | 0.9951 |
71
- | 0.0011 | 13.0 | 25753 | 0.0355 | 0.9290 | 0.9511 | 0.9399 | 0.9951 |
72
- | 0.0009 | 14.0 | 27734 | 0.0307 | 0.9405 | 0.9461 | 0.9433 | 0.9954 |
73
- | 0.0009 | 15.0 | 29715 | 0.0336 | 0.9420 | 0.9430 | 0.9425 | 0.9953 |
74
- | 0.0006 | 16.0 | 31696 | 0.0351 | 0.9357 | 0.9446 | 0.9401 | 0.9950 |
75
- | 0.0007 | 17.0 | 33677 | 0.0326 | 0.9358 | 0.9484 | 0.9420 | 0.9952 |
76
- | 0.0008 | 18.0 | 35658 | 0.0345 | 0.9269 | 0.9549 | 0.9407 | 0.9951 |
77
- | 0.0007 | 19.0 | 37639 | 0.0347 | 0.9352 | 0.9523 | 0.9437 | 0.9953 |
78
- | 0.0005 | 20.0 | 39620 | 0.0344 | 0.9381 | 0.9509 | 0.9445 | 0.9956 |
79
- | 0.0006 | 21.0 | 41601 | 0.0360 | 0.9375 | 0.9498 | 0.9436 | 0.9953 |
80
- | 0.0004 | 22.0 | 43582 | 0.0365 | 0.9429 | 0.9473 | 0.9451 | 0.9954 |
81
- | 0.0005 | 23.0 | 45563 | 0.0362 | 0.9388 | 0.9495 | 0.9441 | 0.9952 |
82
- | 0.0004 | 24.0 | 47544 | 0.0384 | 0.9410 | 0.9444 | 0.9427 | 0.9951 |
83
- | 0.0003 | 25.0 | 49525 | 0.0361 | 0.9445 | 0.9479 | 0.9461 | 0.9956 |
84
- | 0.0003 | 26.0 | 51506 | 0.0372 | 0.9459 | 0.9466 | 0.9463 | 0.9955 |
85
- | 0.0004 | 27.0 | 53487 | 0.0390 | 0.9432 | 0.9461 | 0.9446 | 0.9954 |
86
- | 0.0003 | 28.0 | 55468 | 0.0381 | 0.9412 | 0.9466 | 0.9439 | 0.9955 |
87
- | 0.0004 | 29.0 | 57449 | 0.0404 | 0.9312 | 0.9540 | 0.9424 | 0.9952 |
88
- | 0.0002 | 30.0 | 59430 | 0.0397 | 0.9389 | 0.9509 | 0.9449 | 0.9955 |
89
- | 0.0003 | 31.0 | 61411 | 0.0388 | 0.9413 | 0.9488 | 0.9450 | 0.9954 |
90
- | 0.0002 | 32.0 | 63392 | 0.0409 | 0.9411 | 0.9473 | 0.9442 | 0.9953 |
91
- | 0.0003 | 33.0 | 65373 | 0.0418 | 0.9443 | 0.9509 | 0.9476 | 0.9955 |
92
- | 0.0002 | 34.0 | 67354 | 0.0413 | 0.9390 | 0.9529 | 0.9459 | 0.9955 |
93
- | 0.0001 | 35.0 | 69335 | 0.0418 | 0.9371 | 0.9516 | 0.9443 | 0.9953 |
94
- | 0.0001 | 36.0 | 71316 | 0.0427 | 0.9414 | 0.9525 | 0.9469 | 0.9955 |
95
- | 0.0001 | 37.0 | 73297 | 0.0439 | 0.9359 | 0.9538 | 0.9448 | 0.9953 |
96
- | 0.0001 | 38.0 | 75278 | 0.0418 | 0.9429 | 0.9509 | 0.9469 | 0.9955 |
97
- | 0.0 | 39.0 | 77259 | 0.0410 | 0.9511 | 0.9482 | 0.9497 | 0.9957 |
98
- | 0.0001 | 40.0 | 79240 | 0.0410 | 0.9473 | 0.9507 | 0.9490 | 0.9956 |
99
- | 0.0 | 41.0 | 81221 | 0.0442 | 0.9444 | 0.9532 | 0.9488 | 0.9956 |
100
- | 0.0001 | 42.0 | 83202 | 0.0419 | 0.9427 | 0.9522 | 0.9474 | 0.9956 |
101
- | 0.0001 | 43.0 | 85183 | 0.0423 | 0.9506 | 0.9477 | 0.9491 | 0.9956 |
102
- | 0.0001 | 44.0 | 87164 | 0.0426 | 0.9478 | 0.9498 | 0.9488 | 0.9956 |
103
- | 0.0001 | 45.0 | 89145 | 0.0426 | 0.9425 | 0.9523 | 0.9474 | 0.9956 |
104
- | 0.0 | 46.0 | 91126 | 0.0435 | 0.9433 | 0.9509 | 0.9471 | 0.9956 |
105
- | 0.0 | 47.0 | 93107 | 0.0437 | 0.9458 | 0.9500 | 0.9479 | 0.9956 |
106
- | 0.0 | 48.0 | 95088 | 0.0436 | 0.9458 | 0.9516 | 0.9487 | 0.9957 |
107
- | 0.0 | 49.0 | 97069 | 0.0428 | 0.9483 | 0.9507 | 0.9495 | 0.9957 |
108
- | 0.0 | 50.0 | 99050 | 0.0429 | 0.9487 | 0.9514 | 0.9501 | 0.9957 |
109
-
110
-
111
  ### Framework versions
112
 
113
  - Transformers 4.48.3
 
3
  base_model: google-bert/bert-base-chinese
4
  tags:
5
  - generated_from_trainer
 
 
 
 
 
6
  model-index:
7
  - name: ner_based_bert-base-chinese
8
  results: []
 
15
 
16
  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.
17
  It achieves the following results on the evaluation set:
18
+ - eval_loss: 0.0233
19
+ - eval_precision: 0.9512
20
+ - eval_recall: 0.9627
21
+ - eval_f1: 0.9569
22
+ - eval_accuracy: 0.9965
23
+ - eval_runtime: 13.2938
24
+ - eval_samples_per_second: 480.975
25
+ - eval_steps_per_second: 7.522
26
+ - epoch: 13.0
27
+ - step: 11700
28
 
29
  ## Model description
30
 
 
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 2e-05
47
+ - train_batch_size: 64
48
+ - eval_batch_size: 64
49
  - seed: 42
50
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 30
53
  - mixed_precision_training: Native AMP
54
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  ### Framework versions
56
 
57
  - Transformers 4.48.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06e5ec2e381fb0e60eb8daeb400e65f7737b3a91322c0f3c7c68983023b0c228
3
  size 406799208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15759aa0da5fd924d4cd72023dba775e1ba2a3feb85871b18ec18cee17482973
3
  size 406799208
tokenizer.json CHANGED
@@ -2,7 +2,7 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 512,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 128,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f6eea4ee35082053966d309eafd0a364bdaf832cdab40f71b66c5383ed369f7
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c1d585d377bc9eabd6a90b33fcdea758fda45b757232dacfec5e72f9b417ecd
3
  size 5304