Hugging Face's logo

jefftherover
/
pii-layout-synth-v4

Token Classification
Transformers
Safetensors
modernbert
trackio
Generated from Trainer
Model card Files
xet
 Metrics Community
jefftherover commited on
Commit
e95be83
·
verified ·
1 Parent(s): bffe1f6

End of training

Browse files
Files changed (4) hide show
  1. README.md +91 -0
  2. model.safetensors +1 -1
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +17 -0
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: answerdotai/ModernBERT-base
5
+ tags:
6
+ - trackio
7
+ - trackio:https://huggingface.co/spaces/jefftherover/huggingface-static-c1d769
8
+ - generated_from_trainer
9
+ metrics:
10
+ - precision
11
+ - recall
12
+ - f1
13
+ - accuracy
14
+ model-index:
15
+ - name: pii-layout-synth-v4
16
+ results: []
17
+ ---
18
+ <a href="https://huggingface.co/spaces/jefftherover/huggingface-static-c1d769" target="_blank"><img src="https://raw.githubusercontent.com/gradio-app/trackio/refs/heads/main/trackio/assets/badge.png" alt="Visualize in Trackio" title="Visualize in Trackio" style="height: 40px;"/></a>
19
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
20
+ should probably proofread and complete it, then remove this comment. -->
21
+
22
+ # pii-layout-synth-v4
23
+
24
+ This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
25
+ It achieves the following results on the evaluation set:
26
+ - Loss: 0.0060
27
+ - Precision: 0.9903
28
+ - Recall: 0.9940
29
+ - F1: 0.9921
30
+ - Accuracy: 0.9985
31
+
32
+ ## Model description
33
+
34
+ More information needed
35
+
36
+ ## Intended uses & limitations
37
+
38
+ More information needed
39
+
40
+ ## Training and evaluation data
41
+
42
+ More information needed
43
+
44
+ ## Training procedure
45
+
46
+ ### Training hyperparameters
47
+
48
+ The following hyperparameters were used during training:
49
+ - learning_rate: 5e-05
50
+ - train_batch_size: 16
51
+ - eval_batch_size: 32
52
+ - seed: 42
53
+ - gradient_accumulation_steps: 2
54
+ - total_train_batch_size: 32
55
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
56
+ - lr_scheduler_type: cosine_with_restarts
57
+ - lr_scheduler_warmup_steps: 0.1
58
+ - num_epochs: 5
59
+ - mixed_precision_training: Native AMP
60
+
61
+ ### Training results
62
+
63
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
64
+ |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
65
+ | 0.0883 | 0.2389 | 500 | 0.0336 | 0.9182 | 0.9523 | 0.9349 | 0.9900 |
66
+ | 0.0415 | 0.4778 | 1000 | 0.0155 | 0.9645 | 0.9770 | 0.9707 | 0.9955 |
67
+ | 0.0277 | 0.7167 | 1500 | 0.0119 | 0.9740 | 0.9876 | 0.9808 | 0.9965 |
68
+ | 0.0187 | 0.9556 | 2000 | 0.0082 | 0.9802 | 0.9897 | 0.9850 | 0.9975 |
69
+ | 0.0082 | 1.1945 | 2500 | 0.0081 | 0.9847 | 0.9911 | 0.9879 | 0.9977 |
70
+ | 0.0118 | 1.4333 | 3000 | 0.0077 | 0.9838 | 0.9900 | 0.9869 | 0.9976 |
71
+ | 0.0161 | 1.6722 | 3500 | 0.0102 | 0.9792 | 0.9894 | 0.9843 | 0.9968 |
72
+ | 0.0106 | 1.9111 | 4000 | 0.0064 | 0.9859 | 0.9905 | 0.9882 | 0.9980 |
73
+ | 0.0046 | 2.1500 | 4500 | 0.0057 | 0.9882 | 0.9928 | 0.9905 | 0.9983 |
74
+ | 0.0057 | 2.3889 | 5000 | 0.0062 | 0.9882 | 0.9930 | 0.9906 | 0.9983 |
75
+ | 0.0055 | 2.6278 | 5500 | 0.0055 | 0.9886 | 0.9946 | 0.9916 | 0.9984 |
76
+ | 0.0054 | 2.8667 | 6000 | 0.0057 | 0.9886 | 0.9927 | 0.9907 | 0.9983 |
77
+ | 0.0019 | 3.1056 | 6500 | 0.0065 | 0.9899 | 0.9942 | 0.9920 | 0.9984 |
78
+ | 0.0023 | 3.3445 | 7000 | 0.0060 | 0.9891 | 0.9943 | 0.9917 | 0.9984 |
79
+ | 0.0019 | 3.5834 | 7500 | 0.0061 | 0.9890 | 0.9930 | 0.9910 | 0.9984 |
80
+ | 0.0017 | 3.8223 | 8000 | 0.0057 | 0.9908 | 0.9944 | 0.9926 | 0.9986 |
81
+ | 0.0008 | 4.0612 | 8500 | 0.0056 | 0.9902 | 0.9945 | 0.9923 | 0.9986 |
82
+ | 0.0004 | 4.3000 | 9000 | 0.0060 | 0.9901 | 0.9942 | 0.9922 | 0.9985 |
83
+ | 0.0004 | 4.5389 | 9500 | 0.0060 | 0.9903 | 0.9940 | 0.9921 | 0.9985 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 5.11.0
89
+ - Pytorch 2.12.0+cu130
90
+ - Datasets 5.0.0
91
+ - Tokenizers 0.22.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8caca2fa00383ee3101d0c304d916c68ff7267a5c9645f7baea2aa82c869960
3
  size 598615124
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3450c04a0bd322a7e829ec661a46f88e6b6bf2185e5140c96d7ec5a7577010f5
3
  size 598615124
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_input_names": [
9
+ "input_ids",
10
+ "attention_mask"
11
+ ],
12
+ "model_max_length": 8192,
13
+ "pad_token": "[PAD]",
14
+ "sep_token": "[SEP]",
15
+ "tokenizer_class": "TokenizersBackend",
16
+ "unk_token": "[UNK]"
17
+ }