Hugging Face's logo

Criser2013
/
NER-finetuning-BERT-UNCASED-BIOBERT

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Eval Results
Model card Files Metrics Community
Criser2013 commited on
Commit
9eff247
·
verified ·
1 Parent(s): 4d78455

End of training

Browse files
Files changed (18) hide show
  1. README.md +100 -0
  2. config.json +90 -0
  3. model.safetensors +3 -0
  4. runs/Nov08_20-49-02_dbb934fbe053/events.out.tfevents.1731098948.dbb934fbe053.30.0 +3 -0
  5. runs/Nov08_20-49-02_dbb934fbe053/events.out.tfevents.1731099108.dbb934fbe053.30.1 +3 -0
  6. runs/Nov08_20-49-02_dbb934fbe053/events.out.tfevents.1731099128.dbb934fbe053.30.2 +3 -0
  7. runs/Nov08_20-53-52_dbb934fbe053/events.out.tfevents.1731099252.dbb934fbe053.30.3 +3 -0
  8. runs/Nov08_21-00-19_15ab4e926294/events.out.tfevents.1731099625.15ab4e926294.31.0 +3 -0
  9. runs/Nov08_21-03-42_96820061fa0e/events.out.tfevents.1731099826.96820061fa0e.31.0 +3 -0
  10. runs/Nov08_21-03-42_96820061fa0e/events.out.tfevents.1731100078.96820061fa0e.31.1 +3 -0
  11. runs/Nov08_21-08-50_96820061fa0e/events.out.tfevents.1731100133.96820061fa0e.31.2 +3 -0
  12. runs/Nov08_21-23-29_e16654a8a9f6/events.out.tfevents.1731101016.e16654a8a9f6.29.0 +3 -0
  13. runs/Nov08_21-28-10_49b9814660d5/events.out.tfevents.1731101298.49b9814660d5.30.0 +3 -0
  14. special_tokens_map.json +7 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +56 -0
  17. training_args.bin +3 -0
  18. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,100 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: google-bert/bert-base-uncased
5
+ tags:
6
+ - generated_from_trainer
7
+ datasets:
8
+ - biobert_json
9
+ metrics:
10
+ - precision
11
+ - recall
12
+ - f1
13
+ - accuracy
14
+ model-index:
15
+ - name: NER-finetuning-BERT-UNCASED-BIOBERT
16
+ results:
17
+ - task:
18
+ name: Token Classification
19
+ type: token-classification
20
+ dataset:
21
+ name: biobert_json
22
+ type: biobert_json
23
+ config: Biobert_json
24
+ split: validation
25
+ args: Biobert_json
26
+ metrics:
27
+ - name: Precision
28
+ type: precision
29
+ value: 0.9432138927426685
30
+ - name: Recall
31
+ type: recall
32
+ value: 0.9667549279199764
33
+ - name: F1
34
+ type: f1
35
+ value: 0.9548393345763614
36
+ - name: Accuracy
37
+ type: accuracy
38
+ value: 0.976488513830286
39
+ ---
40
+
41
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
42
+ should probably proofread and complete it, then remove this comment. -->
43
+
44
+ # NER-finetuning-BERT-UNCASED-BIOBERT
45
+
46
+ This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the biobert_json dataset.
47
+ It achieves the following results on the evaluation set:
48
+ - Loss: 0.1163
49
+ - Precision: 0.9432
50
+ - Recall: 0.9668
51
+ - F1: 0.9548
52
+ - Accuracy: 0.9765
53
+
54
+ ## Model description
55
+
56
+ More information needed
57
+
58
+ ## Intended uses & limitations
59
+
60
+ More information needed
61
+
62
+ ## Training and evaluation data
63
+
64
+ More information needed
65
+
66
+ ## Training procedure
67
+
68
+ ### Training hyperparameters
69
+
70
+ The following hyperparameters were used during training:
71
+ - learning_rate: 2e-05
72
+ - train_batch_size: 16
73
+ - eval_batch_size: 16
74
+ - seed: 42
75
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
76
+ - lr_scheduler_type: linear
77
+ - num_epochs: 10
78
+
79
+ ### Training results
80
+
81
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
82
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
83
+ | 0.4431 | 1.0 | 612 | 0.1173 | 0.9250 | 0.9596 | 0.9420 | 0.9709 |
84
+ | 0.139 | 2.0 | 1224 | 0.1097 | 0.9276 | 0.9724 | 0.9495 | 0.9728 |
85
+ | 0.0933 | 3.0 | 1836 | 0.0957 | 0.9451 | 0.9686 | 0.9567 | 0.9776 |
86
+ | 0.0751 | 4.0 | 2448 | 0.0972 | 0.9392 | 0.9733 | 0.9559 | 0.9771 |
87
+ | 0.0536 | 5.0 | 3060 | 0.0978 | 0.9445 | 0.9705 | 0.9573 | 0.9770 |
88
+ | 0.0468 | 6.0 | 3672 | 0.1044 | 0.9427 | 0.9661 | 0.9543 | 0.9766 |
89
+ | 0.0392 | 7.0 | 4284 | 0.1080 | 0.9396 | 0.9691 | 0.9541 | 0.9765 |
90
+ | 0.0376 | 8.0 | 4896 | 0.1151 | 0.9390 | 0.9696 | 0.9540 | 0.9761 |
91
+ | 0.0293 | 9.0 | 5508 | 0.1128 | 0.9429 | 0.9674 | 0.9550 | 0.9766 |
92
+ | 0.0274 | 10.0 | 6120 | 0.1163 | 0.9432 | 0.9668 | 0.9548 | 0.9765 |
93
+
94
+
95
+ ### Framework versions
96
+
97
+ - Transformers 4.45.1
98
+ - Pytorch 2.4.0
99
+ - Datasets 3.0.1
100
+ - Tokenizers 0.20.0
config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "B_CANCER_CONCEPT",
14
+ "1": "B_CHEMOTHERAPY",
15
+ "2": "B_DATE",
16
+ "3": "B_DRUG",
17
+ "4": "B_FAMILY",
18
+ "5": "B_FREQ",
19
+ "6": "B_IMPLICIT_DATE",
20
+ "7": "B_INTERVAL",
21
+ "8": "B_METRIC",
22
+ "9": "B_OCURRENCE_EVENT",
23
+ "10": "B_QUANTITY",
24
+ "11": "B_RADIOTHERAPY",
25
+ "12": "B_SMOKER_STATUS",
26
+ "13": "B_STAGE",
27
+ "14": "B_SURGERY",
28
+ "15": "B_TNM",
29
+ "16": "I_CANCER_CONCEPT",
30
+ "17": "I_DATE",
31
+ "18": "I_DRUG",
32
+ "19": "I_FAMILY",
33
+ "20": "I_FREQ",
34
+ "21": "I_IMPLICIT_DATE",
35
+ "22": "I_INTERVAL",
36
+ "23": "I_METRIC",
37
+ "24": "I_OCURRENCE_EVENT",
38
+ "25": "I_SMOKER_STATUS",
39
+ "26": "I_STAGE",
40
+ "27": "I_SURGERY",
41
+ "28": "I_TNM",
42
+ "29": "O"
43
+ },
44
+ "initializer_range": 0.02,
45
+ "intermediate_size": 3072,
46
+ "label2id": {
47
+ "B_CANCER_CONCEPT": 0,
48
+ "B_CHEMOTHERAPY": 1,
49
+ "B_DATE": 2,
50
+ "B_DRUG": 3,
51
+ "B_FAMILY": 4,
52
+ "B_FREQ": 5,
53
+ "B_IMPLICIT_DATE": 6,
54
+ "B_INTERVAL": 7,
55
+ "B_METRIC": 8,
56
+ "B_OCURRENCE_EVENT": 9,
57
+ "B_QUANTITY": 10,
58
+ "B_RADIOTHERAPY": 11,
59
+ "B_SMOKER_STATUS": 12,
60
+ "B_STAGE": 13,
61
+ "B_SURGERY": 14,
62
+ "B_TNM": 15,
63
+ "I_CANCER_CONCEPT": 16,
64
+ "I_DATE": 17,
65
+ "I_DRUG": 18,
66
+ "I_FAMILY": 19,
67
+ "I_FREQ": 20,
68
+ "I_IMPLICIT_DATE": 21,
69
+ "I_INTERVAL": 22,
70
+ "I_METRIC": 23,
71
+ "I_OCURRENCE_EVENT": 24,
72
+ "I_SMOKER_STATUS": 25,
73
+ "I_STAGE": 26,
74
+ "I_SURGERY": 27,
75
+ "I_TNM": 28,
76
+ "O": 29
77
+ },
78
+ "layer_norm_eps": 1e-12,
79
+ "max_position_embeddings": 512,
80
+ "model_type": "bert",
81
+ "num_attention_heads": 12,
82
+ "num_hidden_layers": 12,
83
+ "pad_token_id": 0,
84
+ "position_embedding_type": "absolute",
85
+ "torch_dtype": "float32",
86
+ "transformers_version": "4.45.1",
87
+ "type_vocab_size": 2,
88
+ "use_cache": true,
89
+ "vocab_size": 30522
90
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5d9c06701e57a14dd26326ce88fb6553b352909221483fd1863ba4b9758d8b1
3
+ size 435682216
runs/Nov08_20-49-02_dbb934fbe053/events.out.tfevents.1731098948.dbb934fbe053.30.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:593ca877e7c50bef00917372dd1df174050ab6d173e38ba3f57c1b54e0d36cec
3
+ size 6398
runs/Nov08_20-49-02_dbb934fbe053/events.out.tfevents.1731099108.dbb934fbe053.30.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a692f735a35633bc61f1e8294e700a5894a3c759ab5c4b6270e98a33ec42c134
3
+ size 6398
runs/Nov08_20-49-02_dbb934fbe053/events.out.tfevents.1731099128.dbb934fbe053.30.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8f6bedeca89c1b4fbb47726b9212d09e2f15fe728c5e3029f8a4a9ea956e4d3
3
+ size 6398
runs/Nov08_20-53-52_dbb934fbe053/events.out.tfevents.1731099252.dbb934fbe053.30.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa22d46446c3732ecd19a0c0085cbdbd7d2d0c37ef08f8608a112746eed6a03f
3
+ size 12712
runs/Nov08_21-00-19_15ab4e926294/events.out.tfevents.1731099625.15ab4e926294.31.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66bcdb6e48c013ec3890d5a00010458f465a515cd6844b1bfde2941dc87db5d4
3
+ size 4184
runs/Nov08_21-03-42_96820061fa0e/events.out.tfevents.1731099826.96820061fa0e.31.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a424450ffe27a40da5e46d70d382d344b70acb0e3ee9e2a6dad5ce447fbb9c3
3
+ size 6398
runs/Nov08_21-03-42_96820061fa0e/events.out.tfevents.1731100078.96820061fa0e.31.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9a4aa7b77c28e449276b06c68297dbe3b7889cf59e241f93c75cdc3eaaeed5c
3
+ size 6398
runs/Nov08_21-08-50_96820061fa0e/events.out.tfevents.1731100133.96820061fa0e.31.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc95330c5ddf4e2cd360503476a7b50e90a5d3bf7882da3f213beb8a0023c8d8
3
+ size 6398
runs/Nov08_21-23-29_e16654a8a9f6/events.out.tfevents.1731101016.e16654a8a9f6.29.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:777f555a57815bce19da3fe6647f54cf35322f4a8ed61fa0ba4bf760521fd0fc
3
+ size 4184
runs/Nov08_21-28-10_49b9814660d5/events.out.tfevents.1731101298.49b9814660d5.30.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c137e86991a00dbb6894af2d7a34cc7c6b2781de6d1f420086217fc0cb81d65d
3
+ size 14006
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "[PAD]",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "100": {
13
+ "content": "[UNK]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "101": {
21
+ "content": "[CLS]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "102": {
29
+ "content": "[SEP]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "103": {
37
+ "content": "[MASK]",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "clean_up_tokenization_spaces": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:770e18b19aa67a3dc877b41dded38783dfb6e49173f1ce431fb47cd4d9439928
3
+ size 5240
vocab.txt ADDED
The diff for this file is too large to render. See raw diff