Hugging Face's logo

BachelorThesis
/
GerMedBERT_NER_V01_BRONCO_CARDIO

Token Classification
Transformers
Safetensors
German
bert
Inference Endpoints
Model card Files Community
AngryBacteria commited on
Commit
9a02ae4
•
1 Parent(s): edf2b8f

End of training

Browse files
Files changed (8) hide show
  1. README.md +80 -0
  2. config.json +43 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +37 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +55 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: GerMedBERT/medbert-512
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: GerMedBERT_NER_V01_BRONCO_CARDIO
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # GerMedBERT_NER_V01_BRONCO_CARDIO
15
+
16
+ This model is a fine-tuned version of [GerMedBERT/medbert-512](https://huggingface.co/GerMedBERT/medbert-512) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0306
19
+ - Diag: {'precision': 0.7065217391304348, 'recall': 0.6345885634588564, 'f1': 0.6686260102865541, 'number': 717}
20
+ - Med: {'precision': 0.8060029282576867, 'recall': 0.7315614617940199, 'f1': 0.7669801462904912, 'number': 1505}
21
+ - Treat: {'precision': 0.8133640552995391, 'recall': 0.7431578947368421, 'f1': 0.7766776677667767, 'number': 475}
22
+ - Overall Precision: 0.7811
23
+ - Overall Recall: 0.7078
24
+ - Overall F1: 0.7427
25
+ - Overall Accuracy: 0.9903
26
+ - Num Input Tokens Seen: 11575975
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 2e-05
46
+ - train_batch_size: 16
47
+ - eval_batch_size: 16
48
+ - seed: 42
49
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
+ - lr_scheduler_type: linear
51
+ - num_epochs: 4
52
+
53
+ ### Training results
54
+
55
+ | Training Loss | Epoch | Step | Validation Loss | Diag | Med | Treat | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | Input Tokens Seen |
56
+ |:-------------:|:------:|:----:|:---------------:|:---------------------------------------------------------------------------------------------------------:|:----------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|:-----------------:|
57
+ | 0.0611 | 0.2496 | 303 | 0.0509 | {'precision': 0.6265060240963856, 'recall': 0.2900976290097629, 'f1': 0.3965681601525262, 'number': 717} | {'precision': 0.7679127725856698, 'recall': 0.3275747508305648, 'f1': 0.45924545877969264, 'number': 1505} | {'precision': 0.8493150684931506, 'recall': 0.5221052631578947, 'f1': 0.6466753585397653, 'number': 475} | 0.7496 | 0.3519 | 0.4789 | 0.9841 | 725328 |
58
+ | 0.0532 | 0.4992 | 606 | 0.0430 | {'precision': 0.7558139534883721, 'recall': 0.36262203626220363, 'f1': 0.4901036757775683, 'number': 717} | {'precision': 0.8224076281287247, 'recall': 0.4584717607973422, 'f1': 0.5887372013651877, 'number': 1505} | {'precision': 0.7891566265060241, 'recall': 0.5515789473684211, 'f1': 0.6493184634448574, 'number': 475} | 0.8 | 0.4494 | 0.5755 | 0.9860 | 1436640 |
59
+ | 0.0488 | 0.7488 | 909 | 0.0394 | {'precision': 0.6588486140724946, 'recall': 0.4309623430962343, 'f1': 0.521079258010118, 'number': 717} | {'precision': 0.803639846743295, 'recall': 0.5574750830564784, 'f1': 0.6582973715182425, 'number': 1505} | {'precision': 0.8328445747800587, 'recall': 0.5978947368421053, 'f1': 0.696078431372549, 'number': 475} | 0.7724 | 0.5310 | 0.6293 | 0.9872 | 2157328 |
60
+ | 0.0342 | 0.9984 | 1212 | 0.0361 | {'precision': 0.6908713692946058, 'recall': 0.46443514644351463, 'f1': 0.5554628857381151, 'number': 717} | {'precision': 0.76010101010101, 'recall': 0.6, 'f1': 0.6706275529149647, 'number': 1505} | {'precision': 0.8910256410256411, 'recall': 0.5852631578947368, 'f1': 0.7064803049555274, 'number': 475} | 0.7639 | 0.5614 | 0.6471 | 0.9873 | 2891248 |
61
+ | 0.0347 | 1.2479 | 1515 | 0.0368 | {'precision': 0.6760828625235404, 'recall': 0.500697350069735, 'f1': 0.5753205128205129, 'number': 717} | {'precision': 0.7350936967632027, 'recall': 0.573421926910299, 'f1': 0.6442702500933185, 'number': 1505} | {'precision': 0.7641277641277642, 'recall': 0.6547368421052632, 'f1': 0.7052154195011338, 'number': 475} | 0.7259 | 0.5684 | 0.6376 | 0.9871 | 3607825 |
62
+ | 0.0283 | 1.4975 | 1818 | 0.0351 | {'precision': 0.6774193548387096, 'recall': 0.5564853556485355, 'f1': 0.6110260336906584, 'number': 717} | {'precision': 0.7513134851138353, 'recall': 0.5700996677740864, 'f1': 0.6482810729127314, 'number': 1505} | {'precision': 0.8045685279187818, 'recall': 0.6673684210526316, 'f1': 0.7295742232451093, 'number': 475} | 0.7407 | 0.5836 | 0.6528 | 0.9872 | 4320401 |
63
+ | 0.0319 | 1.7471 | 2121 | 0.0329 | {'precision': 0.6723809523809524, 'recall': 0.49232914923291493, 'f1': 0.5684380032206119, 'number': 717} | {'precision': 0.7881619937694704, 'recall': 0.6724252491694352, 'f1': 0.7257081391179634, 'number': 1505} | {'precision': 0.8387978142076503, 'recall': 0.6463157894736842, 'f1': 0.7300832342449465, 'number': 475} | 0.7687 | 0.6199 | 0.6864 | 0.9885 | 5050561 |
64
+ | 0.0269 | 1.9967 | 2424 | 0.0311 | {'precision': 0.720353982300885, 'recall': 0.5676429567642957, 'f1': 0.6349453978159126, 'number': 717} | {'precision': 0.7833850931677019, 'recall': 0.6704318936877076, 'f1': 0.7225205871822412, 'number': 1505} | {'precision': 0.8696883852691218, 'recall': 0.6463157894736842, 'f1': 0.7415458937198067, 'number': 475} | 0.7811 | 0.6389 | 0.7028 | 0.9891 | 5776705 |
65
+ | 0.0268 | 2.2463 | 2727 | 0.0309 | {'precision': 0.6769706336939721, 'recall': 0.6108786610878661, 'f1': 0.6422287390029325, 'number': 717} | {'precision': 0.7624466571834992, 'recall': 0.7122923588039867, 'f1': 0.7365166609412571, 'number': 1505} | {'precision': 0.8233830845771144, 'recall': 0.6968421052631579, 'f1': 0.7548460661345495, 'number': 475} | 0.7499 | 0.6826 | 0.7147 | 0.9891 | 6493709 |
66
+ | 0.0265 | 2.4959 | 3030 | 0.0319 | {'precision': 0.7138103161397671, 'recall': 0.5983263598326359, 'f1': 0.6509863429438543, 'number': 717} | {'precision': 0.7537202380952381, 'recall': 0.6730897009966778, 'f1': 0.7111267111267112, 'number': 1505} | {'precision': 0.8165829145728644, 'recall': 0.6842105263157895, 'f1': 0.7445589919816724, 'number': 475} | 0.7542 | 0.6552 | 0.7012 | 0.9888 | 7214269 |
67
+ | 0.0255 | 2.7455 | 3333 | 0.0314 | {'precision': 0.6806853582554517, 'recall': 0.6094839609483961, 'f1': 0.643119941133186, 'number': 717} | {'precision': 0.7615062761506276, 'recall': 0.7255813953488373, 'f1': 0.7431099013269821, 'number': 1505} | {'precision': 0.7866666666666666, 'recall': 0.7452631578947368, 'f1': 0.7654054054054054, 'number': 475} | 0.7454 | 0.6982 | 0.7210 | 0.9892 | 7947645 |
68
+ | 0.0221 | 2.9951 | 3636 | 0.0295 | {'precision': 0.723916532905297, 'recall': 0.6290097629009763, 'f1': 0.673134328358209, 'number': 717} | {'precision': 0.8135464231354642, 'recall': 0.7102990033222591, 'f1': 0.7584249733948208, 'number': 1505} | {'precision': 0.85, 'recall': 0.7157894736842105, 'f1': 0.7771428571428571, 'number': 475} | 0.7959 | 0.6897 | 0.7390 | 0.9903 | 8667437 |
69
+ | 0.018 | 3.2446 | 3939 | 0.0307 | {'precision': 0.7097288676236044, 'recall': 0.6206415620641562, 'f1': 0.6622023809523809, 'number': 717} | {'precision': 0.7909156452775775, 'recall': 0.7289036544850498, 'f1': 0.7586445366528355, 'number': 1505} | {'precision': 0.8165137614678899, 'recall': 0.7494736842105263, 'f1': 0.7815587266739846, 'number': 475} | 0.7747 | 0.7037 | 0.7375 | 0.9901 | 9388513 |
70
+ | 0.0238 | 3.4942 | 4242 | 0.0312 | {'precision': 0.7024922118380063, 'recall': 0.6290097629009763, 'f1': 0.6637233259749816, 'number': 717} | {'precision': 0.781895937277263, 'recall': 0.7289036544850498, 'f1': 0.7544704264099036, 'number': 1505} | {'precision': 0.8235294117647058, 'recall': 0.7368421052631579, 'f1': 0.7777777777777778, 'number': 475} | 0.7684 | 0.7037 | 0.7347 | 0.9898 | 10103889 |
71
+ | 0.0196 | 3.7438 | 4545 | 0.0303 | {'precision': 0.7142857142857143, 'recall': 0.6276150627615062, 'f1': 0.6681514476614699, 'number': 717} | {'precision': 0.7932761087267525, 'recall': 0.7368770764119601, 'f1': 0.7640372028935583, 'number': 1505} | {'precision': 0.8273381294964028, 'recall': 0.7263157894736842, 'f1': 0.773542600896861, 'number': 475} | 0.7787 | 0.7060 | 0.7406 | 0.9902 | 10831905 |
72
+ | 0.0184 | 3.9934 | 4848 | 0.0306 | {'precision': 0.7065217391304348, 'recall': 0.6345885634588564, 'f1': 0.6686260102865541, 'number': 717} | {'precision': 0.8054133138258961, 'recall': 0.7315614617940199, 'f1': 0.7667130919220054, 'number': 1505} | {'precision': 0.8133640552995391, 'recall': 0.7431578947368421, 'f1': 0.7766776677667767, 'number': 475} | 0.7808 | 0.7078 | 0.7425 | 0.9903 | 11559985 |
73
+
74
+
75
+ ### Framework versions
76
+
77
+ - Transformers 4.40.1
78
+ - Pytorch 2.3.0+cu121
79
+ - Datasets 2.19.0
80
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "GerMedBERT/medbert-512",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-MED",
14
+ "2": "I-MED",
15
+ "3": "B-TREAT",
16
+ "4": "I-TREAT",
17
+ "5": "B-DIAG",
18
+ "6": "I-DIAG"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "B-DIAG": 5,
24
+ "B-MED": 1,
25
+ "B-TREAT": 3,
26
+ "I-DIAG": 6,
27
+ "I-MED": 2,
28
+ "I-TREAT": 4,
29
+ "O": 0
30
+ },
31
+ "layer_norm_eps": 1e-12,
32
+ "max_position_embeddings": 512,
33
+ "model_type": "bert",
34
+ "num_attention_heads": 8,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 0,
37
+ "position_embedding_type": "absolute",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.40.1",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 30000
43
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5927c9053cae38eca15d7545f9180738db19e164edcb59a6a920641b142f868
3
+ size 434007876
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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_lower_case": false,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e83cc94bd3c23816669d94f0aed402ae7150ae01b6bc56d16cbcb09f7718fad5
3
+ size 5048
vocab.txt ADDED
The diff for this file is too large to render. See raw diff