Hugging Face's logo

blaze999
/
pii-ner

Token Classification
Transformers
TensorBoard
Safetensors
deberta-v2
Generated from Trainer
Model card Files
xet
Metrics Community
blaze999 commited on
Commit
728d9bc
·
verified ·
1 Parent(s): 29c2e66

Training complete

Browse files
Files changed (11) hide show
  1. README.md +99 -0
  2. added_tokens.json +3 -0
  3. config.json +45 -0
  4. model.safetensors +3 -0
  5. runs/May25_14-18-10_8b26128e7923/events.out.tfevents.1716647159.8b26128e7923.35.0 +3 -0
  6. runs/May25_14-30-27_8b26128e7923/events.out.tfevents.1716647458.8b26128e7923.423.0 +3 -0
  7. special_tokens_map.json +15 -0
  8. spm.model +3 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +58 -0
  11. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/deberta-v3-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: pii-ner
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
+ # pii-ner
20
+
21
+ This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.5816
24
+ - Precision: 0.3789
25
+ - Recall: 0.2054
26
+ - F1: 0.2664
27
+ - Accuracy: 0.9580
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: 16
49
+ - seed: 42
50
+ - gradient_accumulation_steps: 2
51
+ - total_train_batch_size: 16
52
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
+ - lr_scheduler_type: cosine
54
+ - lr_scheduler_warmup_ratio: 0.1
55
+ - num_epochs: 30
56
+ - mixed_precision_training: Native AMP
57
+
58
+ ### Training results
59
+
60
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
61
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
62
+ | 1.3048 | 1.0 | 14 | 0.7370 | 0.0088 | 0.0438 | 0.0147 | 0.7632 |
63
+ | 0.7328 | 2.0 | 28 | 0.2553 | 0.0 | 0.0 | 0.0 | 0.9350 |
64
+ | 0.2676 | 3.0 | 42 | 0.2095 | 0.7353 | 0.1684 | 0.2740 | 0.9658 |
65
+ | 0.0976 | 4.0 | 56 | 0.2309 | 0.9091 | 0.2020 | 0.3306 | 0.9683 |
66
+ | 0.0664 | 5.0 | 70 | 0.2471 | 0.9242 | 0.2054 | 0.3361 | 0.9685 |
67
+ | 0.1703 | 6.0 | 84 | 0.2893 | 0.9091 | 0.2020 | 0.3306 | 0.9683 |
68
+ | 0.1196 | 7.0 | 98 | 0.2559 | 0.8841 | 0.2054 | 0.3333 | 0.9683 |
69
+ | 0.1805 | 8.0 | 112 | 0.2691 | 0.9091 | 0.2020 | 0.3306 | 0.9683 |
70
+ | 0.1669 | 9.0 | 126 | 0.2651 | 0.9242 | 0.2054 | 0.3361 | 0.9685 |
71
+ | 0.2296 | 10.0 | 140 | 0.3022 | 0.9242 | 0.2054 | 0.3361 | 0.9685 |
72
+ | 0.1731 | 11.0 | 154 | 0.2879 | 0.9091 | 0.2020 | 0.3306 | 0.9682 |
73
+ | 0.1983 | 12.0 | 168 | 0.2824 | 0.8824 | 0.2020 | 0.3288 | 0.9682 |
74
+ | 0.0873 | 13.0 | 182 | 0.3495 | 0.9091 | 0.2020 | 0.3306 | 0.9683 |
75
+ | 0.4 | 14.0 | 196 | 0.3905 | 0.9104 | 0.2054 | 0.3352 | 0.9683 |
76
+ | 0.2142 | 15.0 | 210 | 0.4198 | 0.9104 | 0.2054 | 0.3352 | 0.9683 |
77
+ | 0.2092 | 16.0 | 224 | 0.4395 | 0.9091 | 0.2020 | 0.3306 | 0.9682 |
78
+ | 0.0803 | 17.0 | 238 | 0.4003 | 0.9104 | 0.2054 | 0.3352 | 0.9682 |
79
+ | 0.1509 | 18.0 | 252 | 0.4904 | 0.9104 | 0.2054 | 0.3352 | 0.9683 |
80
+ | 0.1382 | 19.0 | 266 | 0.5018 | 0.9091 | 0.2020 | 0.3306 | 0.9682 |
81
+ | 0.0554 | 20.0 | 280 | 0.5128 | 0.9104 | 0.2054 | 0.3352 | 0.9682 |
82
+ | 0.0595 | 21.0 | 294 | 0.5363 | 0.9104 | 0.2054 | 0.3352 | 0.9682 |
83
+ | 0.0339 | 22.0 | 308 | 0.5518 | 0.9104 | 0.2054 | 0.3352 | 0.9682 |
84
+ | 0.0292 | 23.0 | 322 | 0.5613 | 0.8133 | 0.2054 | 0.3280 | 0.9674 |
85
+ | 0.0368 | 24.0 | 336 | 0.5555 | 0.9104 | 0.2054 | 0.3352 | 0.9682 |
86
+ | 0.0224 | 25.0 | 350 | 0.5709 | 0.3885 | 0.2054 | 0.2687 | 0.9585 |
87
+ | 0.0122 | 26.0 | 364 | 0.5753 | 0.3789 | 0.2054 | 0.2664 | 0.9580 |
88
+ | 0.0332 | 27.0 | 378 | 0.5800 | 0.3789 | 0.2054 | 0.2664 | 0.9580 |
89
+ | 0.02 | 28.0 | 392 | 0.5810 | 0.3789 | 0.2054 | 0.2664 | 0.9580 |
90
+ | 0.0155 | 29.0 | 406 | 0.5816 | 0.3789 | 0.2054 | 0.2664 | 0.9580 |
91
+ | 0.0157 | 30.0 | 420 | 0.5816 | 0.3789 | 0.2054 | 0.2664 | 0.9580 |
92
+
93
+
94
+ ### Framework versions
95
+
96
+ - Transformers 4.39.3
97
+ - Pytorch 2.1.2
98
+ - Datasets 2.18.0
99
+ - Tokenizers 0.15.2
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "O",
12
+ "1": "B-PER",
13
+ "2": "I-PER"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "B-PER": 1,
19
+ "I-PER": 2,
20
+ "O": 0
21
+ },
22
+ "layer_norm_eps": 1e-07,
23
+ "max_position_embeddings": 512,
24
+ "max_relative_positions": -1,
25
+ "model_type": "deberta-v2",
26
+ "norm_rel_ebd": "layer_norm",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pooler_dropout": 0,
31
+ "pooler_hidden_act": "gelu",
32
+ "pooler_hidden_size": 768,
33
+ "pos_att_type": [
34
+ "p2c",
35
+ "c2p"
36
+ ],
37
+ "position_biased_input": false,
38
+ "position_buckets": 256,
39
+ "relative_attention": true,
40
+ "share_att_key": true,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.39.3",
43
+ "type_vocab_size": 0,
44
+ "vocab_size": 128100
45
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e316eb7cf515a4f8752c8884057b94a042289e97321f8cb7499276b807beb9dd
3
+ size 735359804
runs/May25_14-18-10_8b26128e7923/events.out.tfevents.1716647159.8b26128e7923.35.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46f8bed10ac821216251d0e217763e328a57cd2205757439ec1f368c17efb07c
3
+ size 5058
runs/May25_14-30-27_8b26128e7923/events.out.tfevents.1716647458.8b26128e7923.423.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c07595f05645fc29dbca6f6f59c59ba3e5d562fe9471ed4cd4d7e7a36eddf6c
3
+ size 28098
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
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
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e1d5beb1df1309047b0cbd00927f1390cdc084d2ed85104f37c7470251fbbf8
3
+ size 4920