Hugging Face's logo

pabRomero
/
BioBERT-full-finetuned-ner-pablo

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
pabRomero commited on
Commit
720ca6e
•
1 Parent(s): b89ae52

Training in progress, epoch 1

Browse files
Files changed (7) hide show
  1. config.json +67 -67
  2. model.safetensors +1 -1
  3. runs/Aug23_13-44-08_ee1898c059d7/events.out.tfevents.1724420648.ee1898c059d7.1664.1 +3 -0
  4. special_tokens_map.json +7 -7
  5. tokenizer.json +6 -1
  6. tokenizer_config.json +58 -57
  7. training_args.bin +2 -2
config.json CHANGED
@@ -1,67 +1,67 @@
1
- {
2
- "_name_or_path": "dmis-lab/biobert-base-cased-v1.2",
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-Drug",
14
- "2": "I-Drug",
15
- "3": "B-Reason",
16
- "4": "I-Reason",
17
- "5": "B-Route",
18
- "6": "I-Route",
19
- "7": "B-Strength",
20
- "8": "I-Strength",
21
- "9": "B-Form",
22
- "10": "I-Form",
23
- "11": "B-Dosage",
24
- "12": "I-Dosage",
25
- "13": "B-Frequency",
26
- "14": "I-Frequency",
27
- "15": "B-Duration",
28
- "16": "I-Duration",
29
- "17": "B-ADE",
30
- "18": "I-ADE"
31
- },
32
- "initializer_range": 0.02,
33
- "intermediate_size": 3072,
34
- "label2id": {
35
- "B-ADE": 17,
36
- "B-Dosage": 11,
37
- "B-Drug": 1,
38
- "B-Duration": 15,
39
- "B-Form": 9,
40
- "B-Frequency": 13,
41
- "B-Reason": 3,
42
- "B-Route": 5,
43
- "B-Strength": 7,
44
- "I-ADE": 18,
45
- "I-Dosage": 12,
46
- "I-Drug": 2,
47
- "I-Duration": 16,
48
- "I-Form": 10,
49
- "I-Frequency": 14,
50
- "I-Reason": 4,
51
- "I-Route": 6,
52
- "I-Strength": 8,
53
- "O": 0
54
- },
55
- "layer_norm_eps": 1e-12,
56
- "max_position_embeddings": 512,
57
- "model_type": "bert",
58
- "num_attention_heads": 12,
59
- "num_hidden_layers": 12,
60
- "pad_token_id": 0,
61
- "position_embedding_type": "absolute",
62
- "torch_dtype": "float32",
63
- "transformers_version": "4.44.0",
64
- "type_vocab_size": 2,
65
- "use_cache": true,
66
- "vocab_size": 28996
67
- }
 
1
+ {
2
+ "_name_or_path": "dmis-lab/biobert-base-cased-v1.2",
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-Drug",
14
+ "2": "I-Drug",
15
+ "3": "B-Reason",
16
+ "4": "I-Reason",
17
+ "5": "B-Route",
18
+ "6": "I-Route",
19
+ "7": "B-Strength",
20
+ "8": "I-Strength",
21
+ "9": "B-Form",
22
+ "10": "I-Form",
23
+ "11": "B-Dosage",
24
+ "12": "I-Dosage",
25
+ "13": "B-Frequency",
26
+ "14": "I-Frequency",
27
+ "15": "B-Duration",
28
+ "16": "I-Duration",
29
+ "17": "B-ADE",
30
+ "18": "I-ADE"
31
+ },
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": 3072,
34
+ "label2id": {
35
+ "B-ADE": 17,
36
+ "B-Dosage": 11,
37
+ "B-Drug": 1,
38
+ "B-Duration": 15,
39
+ "B-Form": 9,
40
+ "B-Frequency": 13,
41
+ "B-Reason": 3,
42
+ "B-Route": 5,
43
+ "B-Strength": 7,
44
+ "I-ADE": 18,
45
+ "I-Dosage": 12,
46
+ "I-Drug": 2,
47
+ "I-Duration": 16,
48
+ "I-Form": 10,
49
+ "I-Frequency": 14,
50
+ "I-Reason": 4,
51
+ "I-Route": 6,
52
+ "I-Strength": 8,
53
+ "O": 0
54
+ },
55
+ "layer_norm_eps": 1e-12,
56
+ "max_position_embeddings": 512,
57
+ "model_type": "bert",
58
+ "num_attention_heads": 12,
59
+ "num_hidden_layers": 12,
60
+ "pad_token_id": 0,
61
+ "position_embedding_type": "absolute",
62
+ "torch_dtype": "float32",
63
+ "transformers_version": "4.44.2",
64
+ "type_vocab_size": 2,
65
+ "use_cache": true,
66
+ "vocab_size": 28996
67
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d0359af1878bff5427366b5ad1316f63151c0ec04516312d0c8e78ec80d54d9
3
  size 430960500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef7ce12cfa60ce078500b6a5cd297574bda4fdcb5b18428fbc4a53131682b8f3
3
  size 430960500
runs/Aug23_13-44-08_ee1898c059d7/events.out.tfevents.1724420648.ee1898c059d7.1664.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f822466ab91a74783129344e38cb714980ade51f03b18ecd9c314204eb31f084
3
+ size 6185
special_tokens_map.json CHANGED
@@ -1,7 +1,7 @@
1
- {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
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 CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
tokenizer_config.json CHANGED
@@ -1,57 +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": true,
48
- "mask_token": "[MASK]",
49
- "model_max_length": 1000000000000000019884624838656,
50
- "never_split": null,
51
- "pad_token": "[PAD]",
52
- "sep_token": "[SEP]",
53
- "strip_accents": null,
54
- "tokenize_chinese_chars": true,
55
- "tokenizer_class": "BertTokenizer",
56
- "unk_token": "[UNK]"
57
- }
 
 
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": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": true,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:536d13184a21e5b93ad3b827b7b9a81a138a0d1aae4db99ef10dc0ccaf0cc5f1
3
- size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6353547446b2e6402f3c16efe4a642782b94740fd37e3f657caae2087ee05c2b
3
+ size 5240