pabRomero commited on
Commit
13852ea
1 Parent(s): 69e363d

Training in progress, epoch 0

Browse files
config.json CHANGED
@@ -1,68 +1,68 @@
1
- {
2
- "_name_or_path": "pabRomero/BERT-full-finetuned-ner-pablo",
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": "O",
14
- "1": "B-Drug",
15
- "2": "I-Drug",
16
- "3": "B-Reason",
17
- "4": "I-Reason",
18
- "5": "B-Route",
19
- "6": "I-Route",
20
- "7": "B-Strength",
21
- "8": "I-Strength",
22
- "9": "B-Form",
23
- "10": "I-Form",
24
- "11": "B-Dosage",
25
- "12": "I-Dosage",
26
- "13": "B-Frequency",
27
- "14": "I-Frequency",
28
- "15": "B-Duration",
29
- "16": "I-Duration",
30
- "17": "B-ADE",
31
- "18": "I-ADE"
32
- },
33
- "initializer_range": 0.02,
34
- "intermediate_size": 3072,
35
- "label2id": {
36
- "B-ADE": 17,
37
- "B-Dosage": 11,
38
- "B-Drug": 1,
39
- "B-Duration": 15,
40
- "B-Form": 9,
41
- "B-Frequency": 13,
42
- "B-Reason": 3,
43
- "B-Route": 5,
44
- "B-Strength": 7,
45
- "I-ADE": 18,
46
- "I-Dosage": 12,
47
- "I-Drug": 2,
48
- "I-Duration": 16,
49
- "I-Form": 10,
50
- "I-Frequency": 14,
51
- "I-Reason": 4,
52
- "I-Route": 6,
53
- "I-Strength": 8,
54
- "O": 0
55
- },
56
- "layer_norm_eps": 1e-12,
57
- "max_position_embeddings": 512,
58
- "model_type": "bert",
59
- "num_attention_heads": 12,
60
- "num_hidden_layers": 12,
61
- "pad_token_id": 0,
62
- "position_embedding_type": "absolute",
63
- "torch_dtype": "float32",
64
- "transformers_version": "4.44.0",
65
- "type_vocab_size": 2,
66
- "use_cache": true,
67
- "vocab_size": 30522
68
- }
 
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": "O",
14
+ "1": "B-Drug",
15
+ "2": "I-Drug",
16
+ "3": "B-Reason",
17
+ "4": "I-Reason",
18
+ "5": "B-Route",
19
+ "6": "I-Route",
20
+ "7": "B-Strength",
21
+ "8": "I-Strength",
22
+ "9": "B-Form",
23
+ "10": "I-Form",
24
+ "11": "B-Dosage",
25
+ "12": "I-Dosage",
26
+ "13": "B-Frequency",
27
+ "14": "I-Frequency",
28
+ "15": "B-Duration",
29
+ "16": "I-Duration",
30
+ "17": "B-ADE",
31
+ "18": "I-ADE"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "B-ADE": 17,
37
+ "B-Dosage": 11,
38
+ "B-Drug": 1,
39
+ "B-Duration": 15,
40
+ "B-Form": 9,
41
+ "B-Frequency": 13,
42
+ "B-Reason": 3,
43
+ "B-Route": 5,
44
+ "B-Strength": 7,
45
+ "I-ADE": 18,
46
+ "I-Dosage": 12,
47
+ "I-Drug": 2,
48
+ "I-Duration": 16,
49
+ "I-Form": 10,
50
+ "I-Frequency": 14,
51
+ "I-Reason": 4,
52
+ "I-Route": 6,
53
+ "I-Strength": 8,
54
+ "O": 0
55
+ },
56
+ "layer_norm_eps": 1e-12,
57
+ "max_position_embeddings": 512,
58
+ "model_type": "bert",
59
+ "num_attention_heads": 12,
60
+ "num_hidden_layers": 12,
61
+ "pad_token_id": 0,
62
+ "position_embedding_type": "absolute",
63
+ "torch_dtype": "float32",
64
+ "transformers_version": "4.44.0",
65
+ "type_vocab_size": 2,
66
+ "use_cache": true,
67
+ "vocab_size": 30522
68
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c6e8260bf8b81f4b63179e5bd5fd600c91596809c8215b4bfd5f9591d0f0470
3
  size 435648380
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7df32043044535148807d9474ca2562c7321815feb34db96acfae731ffb67181
3
  size 435648380
runs/Aug20_15-46-03_669c7f3efb42/events.out.tfevents.1724168764.669c7f3efb42.2417.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d69506fd0c323328e467f8a42dea0f0c164207b2e84b597893e326b716e873ab
3
+ size 6207
special_tokens_map.json CHANGED
@@ -1,37 +1,7 @@
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
- }
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer_config.json CHANGED
@@ -1,59 +1,56 @@
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_lower_case": true,
47
- "mask_token": "[MASK]",
48
- "max_length": 512,
49
- "model_max_length": 512,
50
- "pad_token": "[PAD]",
51
- "sep_token": "[SEP]",
52
- "stride": 0,
53
- "strip_accents": null,
54
- "tokenize_chinese_chars": true,
55
- "tokenizer_class": "BertTokenizer",
56
- "truncation_side": "right",
57
- "truncation_strategy": "longest_first",
58
- "unk_token": "[UNK]"
59
- }
 
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_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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c77ce4e2fc59712e40a132267af0460bb3f6ce823b045ee7b6d3ef277f0fde12
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:483df06b40f3749f5ee7f858c84f0043fa66404150d063ea6dde273207f7bb12
3
  size 5176