Hugging Face's logo

polygraf-ai
/
pii-small

Token Classification
Transformers
Rust
ONNX
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
toghrultahirov commited on
Commit
5a5aea4
•
1 Parent(s): e1d87bb

Training complete

Browse files
Files changed (2) hide show
  1. README.md +25 -25
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- license: mit
3
- base_model: prajjwal1/bert-mini
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # pii_mini
20
 
21
- This model is a fine-tuned version of [prajjwal1/bert-mini](https://huggingface.co/prajjwal1/bert-mini) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.3574
24
- - Precision: 0.5662
25
- - Recall: 0.6433
26
- - F1: 0.6023
27
- - Accuracy: 0.9164
28
 
29
  ## Model description
30
 
@@ -44,8 +44,8 @@ More information needed
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 3e-05
47
- - train_batch_size: 512
48
- - eval_batch_size: 512
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
@@ -55,21 +55,21 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
- | No log | 1.0 | 77 | 2.1303 | 0.0187 | 0.0171 | 0.0178 | 0.6724 |
59
- | No log | 2.0 | 154 | 1.4871 | 0.1477 | 0.1360 | 0.1416 | 0.7600 |
60
- | No log | 3.0 | 231 | 1.1267 | 0.1855 | 0.2342 | 0.2071 | 0.8021 |
61
- | No log | 4.0 | 308 | 0.8904 | 0.2477 | 0.3058 | 0.2737 | 0.8284 |
62
- | No log | 5.0 | 385 | 0.7215 | 0.3154 | 0.3867 | 0.3474 | 0.8497 |
63
- | No log | 6.0 | 462 | 0.6101 | 0.4068 | 0.4814 | 0.4410 | 0.8729 |
64
- | 1.4156 | 7.0 | 539 | 0.5363 | 0.4565 | 0.5364 | 0.4932 | 0.8854 |
65
- | 1.4156 | 8.0 | 616 | 0.4829 | 0.4820 | 0.5618 | 0.5188 | 0.8949 |
66
- | 1.4156 | 9.0 | 693 | 0.4438 | 0.5038 | 0.5825 | 0.5403 | 0.9018 |
67
- | 1.4156 | 10.0 | 770 | 0.4132 | 0.5240 | 0.6011 | 0.5599 | 0.9066 |
68
- | 1.4156 | 11.0 | 847 | 0.3922 | 0.5373 | 0.6157 | 0.5738 | 0.9100 |
69
- | 1.4156 | 12.0 | 924 | 0.3761 | 0.5503 | 0.6256 | 0.5855 | 0.9130 |
70
- | 0.4966 | 13.0 | 1001 | 0.3659 | 0.5590 | 0.6371 | 0.5955 | 0.9151 |
71
- | 0.4966 | 14.0 | 1078 | 0.3592 | 0.5645 | 0.6418 | 0.6007 | 0.9162 |
72
- | 0.4966 | 15.0 | 1155 | 0.3574 | 0.5662 | 0.6433 | 0.6023 | 0.9164 |
73
 
74
 
75
  ### Framework versions
 
1
  ---
2
+ license: apache-2.0
3
+ base_model: google/bert_uncased_L-8_H-512_A-8
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
18
 
19
  # pii_mini
20
 
21
+ This model is a fine-tuned version of [google/bert_uncased_L-8_H-512_A-8](https://huggingface.co/google/bert_uncased_L-8_H-512_A-8) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.1113
24
+ - Precision: 0.9001
25
+ - Recall: 0.9290
26
+ - F1: 0.9143
27
+ - Accuracy: 0.9645
28
 
29
  ## Model description
30
 
 
44
 
45
  The following hyperparameters were used during training:
46
  - learning_rate: 3e-05
47
+ - train_batch_size: 256
48
+ - eval_batch_size: 256
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
 
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | No log | 1.0 | 153 | 0.3797 | 0.4943 | 0.5523 | 0.5217 | 0.9024 |
59
+ | No log | 2.0 | 306 | 0.1868 | 0.7281 | 0.7917 | 0.7586 | 0.9419 |
60
+ | No log | 3.0 | 459 | 0.1319 | 0.8339 | 0.8735 | 0.8532 | 0.9565 |
61
+ | 0.5069 | 4.0 | 612 | 0.1098 | 0.8690 | 0.8990 | 0.8837 | 0.9603 |
62
+ | 0.5069 | 5.0 | 765 | 0.0971 | 0.8725 | 0.9082 | 0.8900 | 0.9647 |
63
+ | 0.5069 | 6.0 | 918 | 0.0924 | 0.8887 | 0.9179 | 0.9031 | 0.9653 |
64
+ | 0.1032 | 7.0 | 1071 | 0.0920 | 0.8820 | 0.9175 | 0.8994 | 0.9632 |
65
+ | 0.1032 | 8.0 | 1224 | 0.0869 | 0.8886 | 0.9219 | 0.9050 | 0.9652 |
66
+ | 0.1032 | 9.0 | 1377 | 0.0912 | 0.8917 | 0.9235 | 0.9073 | 0.9649 |
67
+ | 0.0719 | 10.0 | 1530 | 0.0875 | 0.8995 | 0.9271 | 0.9131 | 0.9666 |
68
+ | 0.0719 | 11.0 | 1683 | 0.0964 | 0.8971 | 0.9264 | 0.9115 | 0.9649 |
69
+ | 0.0719 | 12.0 | 1836 | 0.1006 | 0.9030 | 0.9293 | 0.9159 | 0.9656 |
70
+ | 0.0719 | 13.0 | 1989 | 0.1011 | 0.8978 | 0.9291 | 0.9132 | 0.9639 |
71
+ | 0.0539 | 14.0 | 2142 | 0.1071 | 0.9007 | 0.9275 | 0.9139 | 0.9628 |
72
+ | 0.0539 | 15.0 | 2295 | 0.1113 | 0.9001 | 0.9290 | 0.9143 | 0.9645 |
73
 
74
 
75
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:693cbaf8fa25c904c0cf60a61e817a65577d8c77a267ce8ac511fb27b75e100a
3
  size 164689684
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a1ee7b9ddcf5ffff2d8f9982f7b35b38180baf9bd52bda4a6d85fbcf729e39
3
  size 164689684