mrojas commited on
Commit
880ab92
1 Parent(s): 7d429c6

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "plncmm/roberta-clinical-wl-es",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "O",
16
+ "1": "B-Disease",
17
+ "2": "I-Disease",
18
+ "3": "B-Medication",
19
+ "4": "I-Medication",
20
+ "5": "B-Abbreviation",
21
+ "6": "I-Abbreviation",
22
+ "7": "B-Body_Part",
23
+ "8": "I-Body_Part",
24
+ "9": "B-Family_Member",
25
+ "10": "I-Family_Member",
26
+ "11": "B-Sign_or_Symptom",
27
+ "12": "I-Sign_or_Symptom",
28
+ "13": "B-Laboratory_or_Test_Result",
29
+ "14": "I-Laboratory_or_Test_Result",
30
+ "15": "B-Clinical_Finding",
31
+ "16": "I-Clinical_Finding",
32
+ "17": "B-Diagnostic_Procedure",
33
+ "18": "I-Diagnostic_Procedure",
34
+ "19": "B-Laboratory_Procedure",
35
+ "20": "I-Laboratory_Procedure",
36
+ "21": "B-Therapeutic_Procedure",
37
+ "22": "I-Therapeutic_Procedure"
38
+ },
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 3072,
41
+ "label2id": {
42
+ "B-Abbreviation": 5,
43
+ "B-Body_Part": 7,
44
+ "B-Clinical_Finding": 15,
45
+ "B-Diagnostic_Procedure": 17,
46
+ "B-Disease": 1,
47
+ "B-Family_Member": 9,
48
+ "B-Laboratory_Procedure": 19,
49
+ "B-Laboratory_or_Test_Result": 13,
50
+ "B-Medication": 3,
51
+ "B-Sign_or_Symptom": 11,
52
+ "B-Therapeutic_Procedure": 21,
53
+ "I-Abbreviation": 6,
54
+ "I-Body_Part": 8,
55
+ "I-Clinical_Finding": 16,
56
+ "I-Diagnostic_Procedure": 18,
57
+ "I-Disease": 2,
58
+ "I-Family_Member": 10,
59
+ "I-Laboratory_Procedure": 20,
60
+ "I-Laboratory_or_Test_Result": 14,
61
+ "I-Medication": 4,
62
+ "I-Sign_or_Symptom": 12,
63
+ "I-Therapeutic_Procedure": 22,
64
+ "O": 0
65
+ },
66
+ "layer_norm_eps": 1e-05,
67
+ "max_position_embeddings": 514,
68
+ "model_type": "roberta",
69
+ "num_attention_heads": 12,
70
+ "num_hidden_layers": 12,
71
+ "pad_token_id": 1,
72
+ "position_embedding_type": "absolute",
73
+ "torch_dtype": "float32",
74
+ "transformers_version": "4.24.0",
75
+ "type_vocab_size": 1,
76
+ "use_cache": true,
77
+ "vocab_size": 52000
78
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b889f316249ddb3b7b3790d8ee2a1a18ab375f29b15932564b116b9e204fcd82
3
+ size 501691889
runs/Nov10_21-22-24_262ef5a0a4ac/1668115361.2073786/events.out.tfevents.1668115361.262ef5a0a4ac.78.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57539ac599a7126b8c728741dfd777fe61b097ed2902137622804be30455da36
3
+ size 5474
runs/Nov10_21-22-24_262ef5a0a4ac/events.out.tfevents.1668115361.262ef5a0a4ac.78.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b0bb1d25197a870b56894630b7414c9eed2283f38274442822e78156485f91
3
+ size 5328
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "max_len": 512,
37
+ "name_or_path": "plncmm/roberta-clinical-wl-es",
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "special_tokens_map_file": null,
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20af529abd5e9bd46f61f8b5348048b92e6dd67a02c0632dbbced90889422eed
3
+ size 3375
vocab.json ADDED
The diff for this file is too large to render. See raw diff