hewonty commited on
Commit
93feade
1 Parent(s): 7cd9e8b

Model save

Browse files
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: dslim/bert-base-NER
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: bert-ner-finetuned-pii
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # bert-ner-finetuned-pii
20
+
21
+ This model is a fine-tuned version of [dslim/bert-base-NER](https://huggingface.co/dslim/bert-base-NER) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.0030
24
+ - Precision: 0.6649
25
+ - Recall: 0.4725
26
+ - F1: 0.5525
27
+ - Accuracy: 0.9992
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 2e-05
47
+ - train_batch_size: 8
48
+ - eval_batch_size: 8
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 1
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | 0.0052 | 1.0 | 724 | 0.0030 | 0.6649 | 0.4725 | 0.5525 | 0.9992 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.37.0
64
+ - Pytorch 2.1.2
65
+ - Datasets 2.1.0
66
+ - Tokenizers 0.15.1
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "dslim/bert-base-NER",
3
+ "_num_labels": 9,
4
+ "architectures": [
5
+ "BertForTokenClassification"
6
+ ],
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "classifier_dropout": null,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "B-EMAIL",
14
+ "1": "B-ID_NUM",
15
+ "2": "B-NAME_STUDENT",
16
+ "3": "B-PHONE_NUM",
17
+ "4": "B-STREET_ADDRESS",
18
+ "5": "B-URL_PERSONAL",
19
+ "6": "B-USERNAME",
20
+ "7": "I-ID_NUM",
21
+ "8": "I-NAME_STUDENT",
22
+ "9": "I-PHONE_NUM",
23
+ "10": "I-STREET_ADDRESS",
24
+ "11": "I-URL_PERSONAL",
25
+ "12": "O"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "label2id": {
30
+ "B-EMAIL": 0,
31
+ "B-ID_NUM": 1,
32
+ "B-NAME_STUDENT": 2,
33
+ "B-PHONE_NUM": 3,
34
+ "B-STREET_ADDRESS": 4,
35
+ "B-URL_PERSONAL": 5,
36
+ "B-USERNAME": 6,
37
+ "I-ID_NUM": 7,
38
+ "I-NAME_STUDENT": 8,
39
+ "I-PHONE_NUM": 9,
40
+ "I-STREET_ADDRESS": 10,
41
+ "I-URL_PERSONAL": 11,
42
+ "O": 12
43
+ },
44
+ "layer_norm_eps": 1e-12,
45
+ "max_position_embeddings": 512,
46
+ "model_type": "bert",
47
+ "num_attention_heads": 12,
48
+ "num_hidden_layers": 12,
49
+ "output_past": true,
50
+ "pad_token_id": 0,
51
+ "position_embedding_type": "absolute",
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.37.0",
54
+ "type_vocab_size": 2,
55
+ "use_cache": true,
56
+ "vocab_size": 28996
57
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4bf18abd5132e61eb2f0b77b29395b152b873cc6ee439787848aaec531cae6
3
+ size 430942044
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_len": 512,
50
+ "model_max_length": 512,
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:298576503da7ba1c9d5b5174a3638ea904165cab2d88646022efd4b17faeb269
3
+ size 4728
vocab.txt ADDED
The diff for this file is too large to render. See raw diff