Hugging Face's logo

iiiorg
/
piiranha-v1-detect-personal-information

Token Classification
Transformers
Safetensors
6 languages
deberta-v2
Generated from Trainer
pii
privacy
personaldata
redaction
piidetection
Inference Endpoints
Model card Files Community
6
gaodrew commited on
Commit
9894fa5
•
1 Parent(s): b0066c0

Model save

Browse files
Files changed (2) hide show
  1. README.md +107 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: microsoft/mdeberta-v3-base
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: piiranha-1
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # piiranha-1
21
+
22
+ This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.0173
25
+ - Precision: 0.9316
26
+ - Recall: 0.9308
27
+ - F1: 0.9312
28
+ - Accuracy: 0.9944
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 5e-05
48
+ - train_batch_size: 128
49
+ - eval_batch_size: 128
50
+ - seed: 42
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - lr_scheduler_warmup_ratio: 0.05
54
+ - num_epochs: 5
55
+ - mixed_precision_training: Native AMP
56
+
57
+ ### Training results
58
+
59
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
60
+ |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
61
+ | 0.2984 | 0.0983 | 250 | 0.1005 | 0.5446 | 0.6111 | 0.5759 | 0.9702 |
62
+ | 0.0568 | 0.1965 | 500 | 0.0464 | 0.7895 | 0.8459 | 0.8167 | 0.9849 |
63
+ | 0.0441 | 0.2948 | 750 | 0.0400 | 0.8346 | 0.8669 | 0.8504 | 0.9869 |
64
+ | 0.0368 | 0.3931 | 1000 | 0.0320 | 0.8531 | 0.8784 | 0.8656 | 0.9891 |
65
+ | 0.0323 | 0.4914 | 1250 | 0.0293 | 0.8779 | 0.8889 | 0.8834 | 0.9903 |
66
+ | 0.0287 | 0.5896 | 1500 | 0.0269 | 0.8919 | 0.8836 | 0.8877 | 0.9907 |
67
+ | 0.0282 | 0.6879 | 1750 | 0.0276 | 0.8724 | 0.9012 | 0.8866 | 0.9903 |
68
+ | 0.0268 | 0.7862 | 2000 | 0.0254 | 0.8890 | 0.9041 | 0.8965 | 0.9914 |
69
+ | 0.0264 | 0.8844 | 2250 | 0.0236 | 0.8886 | 0.9040 | 0.8962 | 0.9915 |
70
+ | 0.0243 | 0.9827 | 2500 | 0.0232 | 0.8998 | 0.9033 | 0.9015 | 0.9917 |
71
+ | 0.0213 | 1.0810 | 2750 | 0.0237 | 0.9115 | 0.9040 | 0.9077 | 0.9923 |
72
+ | 0.0213 | 1.1792 | 3000 | 0.0222 | 0.9123 | 0.9143 | 0.9133 | 0.9925 |
73
+ | 0.0217 | 1.2775 | 3250 | 0.0222 | 0.8999 | 0.9169 | 0.9083 | 0.9924 |
74
+ | 0.0209 | 1.3758 | 3500 | 0.0212 | 0.9111 | 0.9133 | 0.9122 | 0.9928 |
75
+ | 0.0204 | 1.4741 | 3750 | 0.0206 | 0.9054 | 0.9203 | 0.9128 | 0.9926 |
76
+ | 0.0183 | 1.5723 | 4000 | 0.0212 | 0.9126 | 0.9160 | 0.9143 | 0.9927 |
77
+ | 0.0191 | 1.6706 | 4250 | 0.0192 | 0.9122 | 0.9192 | 0.9157 | 0.9929 |
78
+ | 0.0185 | 1.7689 | 4500 | 0.0195 | 0.9200 | 0.9191 | 0.9196 | 0.9932 |
79
+ | 0.018 | 1.8671 | 4750 | 0.0188 | 0.9136 | 0.9215 | 0.9176 | 0.9933 |
80
+ | 0.0183 | 1.9654 | 5000 | 0.0191 | 0.9179 | 0.9212 | 0.9196 | 0.9934 |
81
+ | 0.0147 | 2.0637 | 5250 | 0.0188 | 0.9246 | 0.9242 | 0.9244 | 0.9937 |
82
+ | 0.0149 | 2.1619 | 5500 | 0.0184 | 0.9188 | 0.9254 | 0.9221 | 0.9937 |
83
+ | 0.0143 | 2.2602 | 5750 | 0.0193 | 0.9187 | 0.9224 | 0.9205 | 0.9932 |
84
+ | 0.014 | 2.3585 | 6000 | 0.0190 | 0.9246 | 0.9280 | 0.9263 | 0.9936 |
85
+ | 0.0146 | 2.4568 | 6250 | 0.0190 | 0.9225 | 0.9277 | 0.9251 | 0.9936 |
86
+ | 0.0148 | 2.5550 | 6500 | 0.0175 | 0.9297 | 0.9306 | 0.9301 | 0.9942 |
87
+ | 0.0136 | 2.6533 | 6750 | 0.0172 | 0.9191 | 0.9329 | 0.9259 | 0.9938 |
88
+ | 0.0137 | 2.7516 | 7000 | 0.0166 | 0.9299 | 0.9312 | 0.9306 | 0.9942 |
89
+ | 0.014 | 2.8498 | 7250 | 0.0167 | 0.9285 | 0.9313 | 0.9299 | 0.9942 |
90
+ | 0.0128 | 2.9481 | 7500 | 0.0166 | 0.9271 | 0.9326 | 0.9298 | 0.9943 |
91
+ | 0.0113 | 3.0464 | 7750 | 0.0171 | 0.9286 | 0.9347 | 0.9316 | 0.9946 |
92
+ | 0.0103 | 3.1447 | 8000 | 0.0172 | 0.9284 | 0.9383 | 0.9334 | 0.9945 |
93
+ | 0.0104 | 3.2429 | 8250 | 0.0169 | 0.9312 | 0.9406 | 0.9359 | 0.9947 |
94
+ | 0.0094 | 3.3412 | 8500 | 0.0166 | 0.9368 | 0.9359 | 0.9364 | 0.9948 |
95
+ | 0.01 | 3.4395 | 8750 | 0.0166 | 0.9289 | 0.9387 | 0.9337 | 0.9944 |
96
+ | 0.0099 | 3.5377 | 9000 | 0.0162 | 0.9335 | 0.9332 | 0.9334 | 0.9947 |
97
+ | 0.0099 | 3.6360 | 9250 | 0.0160 | 0.9321 | 0.9380 | 0.9350 | 0.9947 |
98
+ | 0.01 | 3.7343 | 9500 | 0.0168 | 0.9306 | 0.9389 | 0.9347 | 0.9947 |
99
+ | 0.0101 | 3.8325 | 9750 | 0.0159 | 0.9339 | 0.9350 | 0.9344 | 0.9947 |
100
+
101
+
102
+ ### Framework versions
103
+
104
+ - Transformers 4.44.2
105
+ - Pytorch 2.4.1+cu121
106
+ - Datasets 3.0.0
107
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06f8f742d9ad1c24136241e711fd170e92fa3904379aad47fde84cd87296d86d
3
  size 1112954872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d503b6804dd734b8f5c9c98c7c38c431cba99778da53987a6945cf1503f3b82
3
  size 1112954872