Hugging Face's logo

mrm8488
/
biomedtra-small-finenuned-clinical-ner

Token Classification
Transformers
PyTorch
TensorBoard
Safetensors
Spanish
electra
clinical
pii
ner
medical
Inference Endpoints
Model card Files Metrics Community
1
mrm8488 commited on
Commit
9c37499
•
1 Parent(s): a8d5dca

First commit

Browse files
Files changed (10) hide show
  1. config.json +80 -0
  2. eval_results.txt +9 -0
  3. pytorch_model.bin +3 -0
  4. runs/Feb26_20-26-36_0ec3306a6e7b/1645907245.9118726/events.out.tfevents.1645907245.0ec3306a6e7b.461.1 +3 -0
  5. runs/Feb26_20-26-36_0ec3306a6e7b/events.out.tfevents.1645907245.0ec3306a6e7b.461.0 +3 -0
  6. runs/Feb26_20-26-36_0ec3306a6e7b/events.out.tfevents.1645907976.0ec3306a6e7b.461.2 +3 -0
  7. special_tokens_map.json +1 -0
  8. tokenizer_config.json +1 -0
  9. training_args.bin +3 -0
  10. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mrm8488/biomedtra-small-es",
3
+ "architectures": [
4
+ "ElectraForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 128,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 256,
12
+ "id2label": {
13
+ "0": "",
14
+ "1": "CALLE",
15
+ "2": "CENTRO_SALUD",
16
+ "3": "CORREO_ELECTRONICO",
17
+ "4": "EDAD_SUJETO_ASISTENCIA",
18
+ "5": "FAMILIARES_SUJETO_ASISTENCIA",
19
+ "6": "FECHAS",
20
+ "7": "HOSPITAL",
21
+ "8": "ID_ASEGURAMIENTO",
22
+ "9": "ID_CONTACTO_ASISTENCIAL",
23
+ "10": "ID_SUJETO_ASISTENCIA",
24
+ "11": "ID_TITULACION_PERSONAL_SANITARIO",
25
+ "12": "INSTITUCION",
26
+ "13": "NOMBRE_PERSONAL_SANITARIO",
27
+ "14": "NOMBRE_SUJETO_ASISTENCIA",
28
+ "15": "NUMERO_FAX",
29
+ "16": "NUMERO_TELEFONO",
30
+ "17": "O",
31
+ "18": "OTROS_SUJETO_ASISTENCIA",
32
+ "19": "PAIS",
33
+ "20": "PROFESION",
34
+ "21": "SEXO_SUJETO_ASISTENCIA",
35
+ "22": "TERRITORIO"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 1024,
39
+ "label2id": {
40
+ "": 0,
41
+ "CALLE": 1,
42
+ "CENTRO_SALUD": 2,
43
+ "CORREO_ELECTRONICO": 3,
44
+ "EDAD_SUJETO_ASISTENCIA": 4,
45
+ "FAMILIARES_SUJETO_ASISTENCIA": 5,
46
+ "FECHAS": 6,
47
+ "HOSPITAL": 7,
48
+ "ID_ASEGURAMIENTO": 8,
49
+ "ID_CONTACTO_ASISTENCIAL": 9,
50
+ "ID_SUJETO_ASISTENCIA": 10,
51
+ "ID_TITULACION_PERSONAL_SANITARIO": 11,
52
+ "INSTITUCION": 12,
53
+ "NOMBRE_PERSONAL_SANITARIO": 13,
54
+ "NOMBRE_SUJETO_ASISTENCIA": 14,
55
+ "NUMERO_FAX": 15,
56
+ "NUMERO_TELEFONO": 16,
57
+ "O": 17,
58
+ "OTROS_SUJETO_ASISTENCIA": 18,
59
+ "PAIS": 19,
60
+ "PROFESION": 20,
61
+ "SEXO_SUJETO_ASISTENCIA": 21,
62
+ "TERRITORIO": 22
63
+ },
64
+ "layer_norm_eps": 1e-12,
65
+ "max_position_embeddings": 512,
66
+ "model_type": "electra",
67
+ "num_attention_heads": 4,
68
+ "num_hidden_layers": 12,
69
+ "pad_token_id": 0,
70
+ "position_embedding_type": "absolute",
71
+ "summary_activation": "gelu",
72
+ "summary_last_dropout": 0.1,
73
+ "summary_type": "first",
74
+ "summary_use_proj": true,
75
+ "torch_dtype": "float32",
76
+ "transformers_version": "4.17.0.dev0",
77
+ "type_vocab_size": 2,
78
+ "use_cache": true,
79
+ "vocab_size": 31002
80
+ }
eval_results.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
1
+ eval_loss = 0.17097021639347076
2
+ eval_accuracy_score = 0.9747292075155622
3
+ eval_precision = 0.6711051930758988
4
+ eval_recall = 0.6480925846549507
5
+ eval_f1 = 0.6593981683384212
6
+ eval_runtime = 6.171
7
+ eval_samples_per_second = 258.629
8
+ eval_steps_per_second = 8.102
9
+ epoch = 64.0
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33dc748f8552ed9d625cdd53f6bf24b0184da93c7ea241283194d51aa811de7e
3
+ size 54287661
runs/Feb26_20-26-36_0ec3306a6e7b/1645907245.9118726/events.out.tfevents.1645907245.0ec3306a6e7b.461.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae5021ad74ad1d70b1bef5002d2affb1398b73d6b5fd9607a2e1e385a78d7012
3
+ size 4730
runs/Feb26_20-26-36_0ec3306a6e7b/events.out.tfevents.1645907245.0ec3306a6e7b.461.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:723949a159fd7861d65414985b2f0c634bbf374027f69a270e7bf47e883526ca
3
+ size 12338
runs/Feb26_20-26-36_0ec3306a6e7b/events.out.tfevents.1645907976.0ec3306a6e7b.461.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f44dd13dc52ffeceea308f56e3973980472b6c51f7dc839dd8278d5e85673de
3
+ size 518
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "mrm8488/biomedtra-small-es", "tokenizer_class": "ElectraTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7aca06e2912ed32964a93600eb21c70185dedfe97b159344e065d8aa077e30a
3
+ size 2991
vocab.txt ADDED
The diff for this file is too large to render. See raw diff