Hugging Face's logo

somukandula
/
maskara-tiny

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
 Community
somukandula commited on
Commit
e9ef61d
·
verified ·
1 Parent(s): 4af944e

Model save

Browse files
Files changed (11) hide show
  1. README.md +30 -31
  2. config.json +1 -1
  3. final/config.json +1 -1
  4. final/model.safetensors +1 -1
  5. final/special_tokens_map.json +35 -5
  6. final/tokenizer_config.json +4 -0
  7. final/training_args.bin +1 -1
  8. model.safetensors +1 -1
  9. special_tokens_map.json +35 -5
  10. tokenizer_config.json +4 -0
  11. training_args.bin +1 -1
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: transformers
3
  license: mit
4
- base_model: nreimers/MiniLM-L6-H384-uncased
5
  tags:
6
  - generated_from_trainer
7
  metrics:
@@ -18,31 +18,31 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # maskara-tiny
20
 
21
- This model is a fine-tuned version of [nreimers/MiniLM-L6-H384-uncased](https://huggingface.co/nreimers/MiniLM-L6-H384-uncased) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.4250
24
- - Precision: 0.7232
25
- - Recall: 0.8242
26
- - F1: 0.7704
27
- - Overall F1: 0.7932
28
- - Address F1: 0.9994
29
- - Api Key F1: 0.9476
30
- - Credit Card F1: 0.3615
31
- - Date Of Birth F1: 0.9542
32
- - Driver License F1: 0.6219
33
- - Email F1: 0.8571
34
- - Ip Address F1: 0.9379
35
- - Password F1: 0.4249
36
- - Person Name F1: 0.8693
37
- - Phone F1: 0.6261
38
- - Ssn F1: 1.0
39
- - Username F1: 0.9406
40
- - Aadhaar F1: 0.6891
41
- - Pan Card F1: 0.8508
42
- - Passport F1: 0.9601
43
- - Upi Id F1: 0.9115
44
- - Vehicle Reg F1: 0.5329
45
- - Indian Id F1: 0.7461
46
 
47
  ## Model description
48
 
@@ -61,23 +61,22 @@ More information needed
61
  ### Training hyperparameters
62
 
63
  The following hyperparameters were used during training:
64
- - learning_rate: 3e-05
65
  - train_batch_size: 32
66
  - eval_batch_size: 64
67
  - seed: 42
68
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
69
  - lr_scheduler_type: linear
70
  - lr_scheduler_warmup_ratio: 0.06
71
- - num_epochs: 5
72
 
73
  ### Training results
74
 
75
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Overall F1 | Address F1 | Api Key F1 | Credit Card F1 | Date Of Birth F1 | Driver License F1 | Email F1 | Ip Address F1 | Password F1 | Person Name F1 | Phone F1 | Ssn F1 | Username F1 | Aadhaar F1 | Pan Card F1 | Passport F1 | Upi Id F1 | Vehicle Reg F1 | Indian Id F1 |
76
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:----------:|:----------:|:----------:|:--------------:|:----------------:|:-----------------:|:--------:|:-------------:|:-----------:|:--------------:|:--------:|:------:|:-----------:|:----------:|:-----------:|:-----------:|:---------:|:--------------:|:------------:|
77
- | 0.0014 | 1.0 | 13345 | 0.5441 | 0.8285 | 0.9357 | 0.8788 | 0.8189 | 0.6667 | 1.0 | 0.0 | 0.9975 | 1.0 | 0.9993 | 1.0 | 0.0 | 0.8449 | 0.8474 | 0.0 | 0.9975 | 0.9712 | 0.9975 | 0.0 | 0.9970 | 0.9652 | 0.9827 |
78
- | 0.0005 | 2.0 | 26690 | 0.6325 | 0.7841 | 0.9183 | 0.8459 | 0.7987 | 0.6661 | 0.9852 | 0.0 | 1.0 | 0.9163 | 1.0 | 1.0 | 0.0 | 0.7942 | 0.7930 | 0.0 | 0.9217 | 0.9475 | 0.9767 | 0.0 | 1.0 | 0.98 | 0.9761 |
79
- | 0.0002 | 3.0 | 40035 | 0.7098 | 0.7712 | 0.9170 | 0.8378 | 0.7400 | 0.6656 | 0.9975 | 0.0 | 0.8299 | 0.9726 | 0.9936 | 1.0 | 0.0 | 0.8229 | 0.7862 | 0.0 | 0.9412 | 0.9537 | 0.9091 | 0.0 | 0.9780 | 0.9900 | 0.9577 |
80
- | 0.0002 | 4.0 | 53380 | 0.7417 | 0.7906 | 0.9108 | 0.8465 | 0.8082 | 0.6633 | 1.0 | 0.0 | 1.0 | 1.0 | 1.0 | 1.0 | 0.0 | 0.8032 | 0.7564 | 0.0 | 0.9852 | 0.9501 | 0.9864 | 0.0 | 1.0 | 0.9779 | 0.9786 |
81
 
82
 
83
  ### Framework versions
 
1
  ---
2
  library_name: transformers
3
  license: mit
4
+ base_model: somukandula/maskara-tiny
5
  tags:
6
  - generated_from_trainer
7
  metrics:
 
18
 
19
  # maskara-tiny
20
 
21
+ This model is a fine-tuned version of [somukandula/maskara-tiny](https://huggingface.co/somukandula/maskara-tiny) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.5828
24
+ - Precision: 0.8369
25
+ - Recall: 0.9271
26
+ - F1: 0.8797
27
+ - Overall F1: 0.8172
28
+ - Address F1: 0.6667
29
+ - Api Key F1: 1.0
30
+ - Credit Card F1: 0.0
31
+ - Date Of Birth F1: 1.0
32
+ - Driver License F1: 0.9875
33
+ - Email F1: 1.0
34
+ - Ip Address F1: 1.0
35
+ - Password F1: 0.0
36
+ - Person Name F1: 0.8378
37
+ - Phone F1: 0.8267
38
+ - Ssn F1: 0.0
39
+ - Username F1: 1.0
40
+ - Aadhaar F1: 0.9637
41
+ - Pan Card F1: 1.0
42
+ - Passport F1: 0.0
43
+ - Upi Id F1: 1.0
44
+ - Vehicle Reg F1: 0.975
45
+ - Indian Id F1: 0.9847
46
 
47
  ## Model description
48
 
 
61
  ### Training hyperparameters
62
 
63
  The following hyperparameters were used during training:
64
+ - learning_rate: 1e-05
65
  - train_batch_size: 32
66
  - eval_batch_size: 64
67
  - seed: 42
68
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
69
  - lr_scheduler_type: linear
70
  - lr_scheduler_warmup_ratio: 0.06
71
+ - num_epochs: 3
72
 
73
  ### Training results
74
 
75
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Overall F1 | Address F1 | Api Key F1 | Credit Card F1 | Date Of Birth F1 | Driver License F1 | Email F1 | Ip Address F1 | Password F1 | Person Name F1 | Phone F1 | Ssn F1 | Username F1 | Aadhaar F1 | Pan Card F1 | Passport F1 | Upi Id F1 | Vehicle Reg F1 | Indian Id F1 |
76
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:----------:|:----------:|:----------:|:--------------:|:----------------:|:-----------------:|:--------:|:-------------:|:-----------:|:--------------:|:--------:|:------:|:-----------:|:----------:|:-----------:|:-----------:|:---------:|:--------------:|:------------:|
77
+ | 0.0006 | 1.0 | 14283 | 0.6201 | 0.7070 | 0.7883 | 0.7454 | 0.7770 | 0.9996 | 0.9888 | 0.2740 | 0.9882 | 0.5042 | 0.6678 | 0.9995 | 0.5025 | 0.8300 | 0.6457 | 1.0 | 0.9623 | 0.6661 | 0.8804 | 0.9544 | 0.9077 | 0.4370 | 0.7228 |
78
+ | 0.0003 | 2.0 | 28566 | 0.4654 | 0.7210 | 0.8069 | 0.7615 | 0.7900 | 0.9998 | 0.9880 | 0.3006 | 0.9835 | 0.5868 | 0.7152 | 0.9667 | 0.6032 | 0.8403 | 0.6424 | 1.0 | 0.9833 | 0.6575 | 0.8424 | 0.8378 | 0.9728 | 0.5097 | 0.7456 |
79
+ | 0.0003 | 3.0 | 42849 | 0.5373 | 0.7026 | 0.8087 | 0.7519 | 0.7755 | 0.9992 | 0.9857 | 0.2915 | 0.9859 | 0.5949 | 0.7581 | 0.9446 | 0.4776 | 0.8277 | 0.6466 | 1.0 | 0.9880 | 0.6732 | 0.8555 | 0.8258 | 0.9161 | 0.4128 | 0.7144 |
 
80
 
81
 
82
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "nreimers/MiniLM-L6-H384-uncased",
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
 
1
  {
2
+ "_name_or_path": "somukandula/maskara-tiny",
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
final/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "nreimers/MiniLM-L6-H384-uncased",
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
 
1
  {
2
+ "_name_or_path": "somukandula/maskara-tiny",
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
final/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fafcc572c27de6fce34880f8191b79962e05bd3a35bd5632275aedd69801e318
3
  size 90327228
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec99d5b73cc1ffc41a161f3dd7e3e30027fbe224b02e53e3912dc9b0b803a17a
3
  size 90327228
final/special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
  }
final/tokenizer_config.json CHANGED
@@ -46,12 +46,16 @@
46
  "do_basic_tokenize": true,
47
  "do_lower_case": true,
48
  "mask_token": "[MASK]",
 
49
  "model_max_length": 512,
50
  "never_split": null,
51
  "pad_token": "[PAD]",
52
  "sep_token": "[SEP]",
 
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
  "tokenizer_class": "BertTokenizer",
 
 
56
  "unk_token": "[UNK]"
57
  }
 
46
  "do_basic_tokenize": true,
47
  "do_lower_case": true,
48
  "mask_token": "[MASK]",
49
+ "max_length": 512,
50
  "model_max_length": 512,
51
  "never_split": null,
52
  "pad_token": "[PAD]",
53
  "sep_token": "[SEP]",
54
+ "stride": 0,
55
  "strip_accents": null,
56
  "tokenize_chinese_chars": true,
57
  "tokenizer_class": "BertTokenizer",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
  "unk_token": "[UNK]"
61
  }
final/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56c9c254fe9a688321b26fa42de1d50518f69d2517a81259eecf282420ef1bc1
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbd413cfed094c4e24cb4765861f95f94cfd1e3eef02cb1de437287662118cd8
3
  size 5240
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fafcc572c27de6fce34880f8191b79962e05bd3a35bd5632275aedd69801e318
3
  size 90327228
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec99d5b73cc1ffc41a161f3dd7e3e30027fbe224b02e53e3912dc9b0b803a17a
3
  size 90327228
special_tokens_map.json CHANGED
@@ -1,7 +1,37 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
  }
tokenizer_config.json CHANGED
@@ -46,12 +46,16 @@
46
  "do_basic_tokenize": true,
47
  "do_lower_case": true,
48
  "mask_token": "[MASK]",
 
49
  "model_max_length": 512,
50
  "never_split": null,
51
  "pad_token": "[PAD]",
52
  "sep_token": "[SEP]",
 
53
  "strip_accents": null,
54
  "tokenize_chinese_chars": true,
55
  "tokenizer_class": "BertTokenizer",
 
 
56
  "unk_token": "[UNK]"
57
  }
 
46
  "do_basic_tokenize": true,
47
  "do_lower_case": true,
48
  "mask_token": "[MASK]",
49
+ "max_length": 512,
50
  "model_max_length": 512,
51
  "never_split": null,
52
  "pad_token": "[PAD]",
53
  "sep_token": "[SEP]",
54
+ "stride": 0,
55
  "strip_accents": null,
56
  "tokenize_chinese_chars": true,
57
  "tokenizer_class": "BertTokenizer",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
  "unk_token": "[UNK]"
61
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56c9c254fe9a688321b26fa42de1d50518f69d2517a81259eecf282420ef1bc1
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbd413cfed094c4e24cb4765861f95f94cfd1e3eef02cb1de437287662118cd8
3
  size 5240