Hugging Face's logo

gyr66
/
Ernie-3.0-base-chinese-finetuned-ner

Token Classification
Transformers
Safetensors
ernie
Generated from Trainer
Inference Endpoints
Model card Files Community
gyr66 commited on
Commit
3f3c3fa
·
1 Parent(s): c424f9f

Update model

Browse files
Files changed (4) hide show
  1. README.md +16 -22
  2. model.safetensors +1 -1
  3. tokenizer_config.json +4 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -9,12 +9,6 @@ metrics:
9
  model-index:
10
  - name: Ernie-3.0-base-chinese-finetuned-ner
11
  results: []
12
- datasets:
13
- - gyr66/privacy_detection
14
- language:
15
- - zh
16
- library_name: transformers
17
- pipeline_tag: token-classification
18
  ---
19
 
20
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -24,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
24
 
25
  This model was trained from scratch on an unknown dataset.
26
  It achieves the following results on the evaluation set:
27
- - Loss: 0.3548
28
- - Precision: 0.6193
29
- - Recall: 0.7467
30
- - F1: 0.6771
31
- - Accuracy: 0.9069
32
 
33
  ## Model description
34
 
@@ -59,16 +53,16 @@ The following hyperparameters were used during training:
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
61
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
62
- | 0.3645 | 1.0 | 126 | 0.3654 | 0.5452 | 0.6712 | 0.6017 | 0.8951 |
63
- | 0.2821 | 2.0 | 252 | 0.3639 | 0.5748 | 0.7127 | 0.6364 | 0.8961 |
64
- | 0.2378 | 3.0 | 378 | 0.3561 | 0.5801 | 0.7263 | 0.6451 | 0.8991 |
65
- | 0.217 | 4.0 | 504 | 0.3531 | 0.6027 | 0.7397 | 0.6642 | 0.9030 |
66
- | 0.2083 | 5.0 | 630 | 0.3640 | 0.5991 | 0.7435 | 0.6635 | 0.8999 |
67
- | 0.1956 | 6.0 | 756 | 0.3488 | 0.6218 | 0.7299 | 0.6715 | 0.9064 |
68
- | 0.18 | 7.0 | 882 | 0.3457 | 0.6207 | 0.7442 | 0.6769 | 0.9072 |
69
- | 0.1696 | 8.0 | 1008 | 0.3543 | 0.6191 | 0.7460 | 0.6766 | 0.9061 |
70
- | 0.1618 | 9.0 | 1134 | 0.3548 | 0.6193 | 0.7467 | 0.6771 | 0.9069 |
71
- | 0.1568 | 10.0 | 1260 | 0.3553 | 0.6180 | 0.7462 | 0.6761 | 0.9063 |
72
 
73
 
74
  ### Framework versions
@@ -76,4 +70,4 @@ The following hyperparameters were used during training:
76
  - Transformers 4.35.2
77
  - Pytorch 2.1.0+cu121
78
  - Datasets 2.16.1
79
- - Tokenizers 0.15.0
 
9
  model-index:
10
  - name: Ernie-3.0-base-chinese-finetuned-ner
11
  results: []
 
 
 
 
 
 
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
18
 
19
  This model was trained from scratch on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4856
22
+ - Precision: 0.6511
23
+ - Recall: 0.7535
24
+ - F1: 0.6986
25
+ - Accuracy: 0.9053
26
 
27
  ## Model description
28
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
55
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
56
+ | 0.0667 | 1.0 | 126 | 0.4589 | 0.6387 | 0.7553 | 0.6921 | 0.9012 |
57
+ | 0.0594 | 2.0 | 252 | 0.4656 | 0.6444 | 0.7515 | 0.6939 | 0.9057 |
58
+ | 0.053 | 3.0 | 378 | 0.4524 | 0.6444 | 0.7477 | 0.6922 | 0.9064 |
59
+ | 0.0473 | 4.0 | 504 | 0.4955 | 0.6298 | 0.7568 | 0.6875 | 0.9012 |
60
+ | 0.0461 | 5.0 | 630 | 0.4892 | 0.6512 | 0.7505 | 0.6973 | 0.9077 |
61
+ | 0.0438 | 6.0 | 756 | 0.5021 | 0.6450 | 0.7528 | 0.6947 | 0.9054 |
62
+ | 0.0428 | 7.0 | 882 | 0.5048 | 0.6471 | 0.7576 | 0.6980 | 0.9050 |
63
+ | 0.0583 | 8.0 | 1008 | 0.4990 | 0.6401 | 0.7533 | 0.6921 | 0.9038 |
64
+ | 0.0582 | 9.0 | 1134 | 0.4833 | 0.6457 | 0.7513 | 0.6945 | 0.9064 |
65
+ | 0.0635 | 10.0 | 1260 | 0.4856 | 0.6511 | 0.7535 | 0.6986 | 0.9053 |
66
 
67
 
68
  ### Framework versions
 
70
  - Transformers 4.35.2
71
  - Pytorch 2.1.0+cu121
72
  - Datasets 2.16.1
73
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f91d99026ad7954852a1bf8906f5684f148bbc78e529fa615cf3bd2d48adf68
3
  size 469529812
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff1eb75663877384e996e1939a7bcd93a6c1a2a855f977af53386c266dae1326
3
  size 469529812
tokenizer_config.json CHANGED
@@ -47,12 +47,16 @@
47
  "do_lower_case": true,
48
  "ignore_mismatched_sizes": true,
49
  "mask_token": "[MASK]",
 
50
  "model_max_length": 1000000000000000019884624838656,
51
  "never_split": null,
52
  "pad_token": "[PAD]",
53
  "sep_token": "[SEP]",
 
54
  "strip_accents": null,
55
  "tokenize_chinese_chars": true,
56
  "tokenizer_class": "BertTokenizer",
 
 
57
  "unk_token": "[UNK]"
58
  }
 
47
  "do_lower_case": true,
48
  "ignore_mismatched_sizes": true,
49
  "mask_token": "[MASK]",
50
+ "max_length": 512,
51
  "model_max_length": 1000000000000000019884624838656,
52
  "never_split": null,
53
  "pad_token": "[PAD]",
54
  "sep_token": "[SEP]",
55
+ "stride": 0,
56
  "strip_accents": null,
57
  "tokenize_chinese_chars": true,
58
  "tokenizer_class": "BertTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
  "unk_token": "[UNK]"
62
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee9bbc5e1c4471260f7c6f5e9be8823e910dec16b7f30b6aae9835e038263833
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b836eaee33d8db30d4101a292d5b9aba4ee92fb6237699f866b88cc32a109a7a
3
  size 4600