cp500 commited on
Commit
bf8291f
1 Parent(s): f4b7c2a

Training in progress, epoch 1

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ vocab.txt filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "imvladikon/alephbertgimmel-base-512",
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": "TEST",
14
+ "1": "OTHER",
15
+ "2": "ANATOMY",
16
+ "3": "REFERRAL",
17
+ "4": "MEDICAL_PROCEDURE",
18
+ "5": "PROTECTED_HEALTH_INFORMATION_EMAIL",
19
+ "6": "SYMPTOM",
20
+ "7": "PULSE",
21
+ "8": "PROTECTED_HEALTH_INFORMATION_PROFESSION",
22
+ "9": "PHYSICAL_EXAM",
23
+ "10": "RISK_FACTOR",
24
+ "11": "PROTECTED_HEALTH_INFORMATION_GENDER",
25
+ "12": "MEDICATION",
26
+ "13": "0",
27
+ "14": "TREATMENT",
28
+ "15": "VITAL_SIGN",
29
+ "16": "MEDICAL_HISTORY",
30
+ "17": "STAGE",
31
+ "18": "MEDICAL_EXAM",
32
+ "19": "FOLLOW_UP",
33
+ "20": "CLINICAL_FINDINGS",
34
+ "21": "DOSAGE",
35
+ "22": "MEASUREMENT",
36
+ "23": "PROTECTED_HEALTH_INFORMATION_PHONE_NUMBER",
37
+ "24": "LAB_FINDING",
38
+ "25": "NEXT_VISIT",
39
+ "26": "DURATION",
40
+ "27": "QUANTITY",
41
+ "28": "ALLERGIES",
42
+ "29": "PROGNOSIS",
43
+ "30": "DIAGNOSIS",
44
+ "31": "EXAMINATION",
45
+ "32": "FREQUENCY",
46
+ "33": "OBSERVATION",
47
+ "34": "AFFECTED_BODY_PARTS",
48
+ "35": "TEMPERATURE",
49
+ "36": "LIFESTYLE",
50
+ "37": "ONSET",
51
+ "38": "PROTECTED_HEALTH_INFORMATION_MEDICAL_RECORD",
52
+ "39": "PROTECTED_HEALTH_INFORMATION_NAME",
53
+ "40": "BLOOD_PRESSURE",
54
+ "41": "IMAGING",
55
+ "42": "RECOMMENDATION",
56
+ "43": "PROTECTED_HEALTH_INFORMATION_AGE",
57
+ "44": "HEART_RATE",
58
+ "45": "FINDINGS",
59
+ "46": "GENDER",
60
+ "47": "OUTCOME",
61
+ "48": "FAMILY_HISTORY",
62
+ "49": "MEDICAL_DEVICE",
63
+ "50": "SPECIALIST",
64
+ "51": "BLOOD_SUGAR",
65
+ "52": "OTHER_DATES",
66
+ "53": "RESPIRATORY_RATE",
67
+ "54": "MEDICAL_CONDITION",
68
+ "55": "PROCEDURE",
69
+ "56": "DEMOGRAPHICS",
70
+ "57": "PROTECTED_HEALTH_INFORMATION_DATE",
71
+ "58": "PROTECTED_HEALTH_INFORMATION_LOCATION"
72
+ },
73
+ "initializer_range": 0.02,
74
+ "intermediate_size": 3072,
75
+ "label2id": {
76
+ "0": 13,
77
+ "AFFECTED_BODY_PARTS": 34,
78
+ "ALLERGIES": 28,
79
+ "ANATOMY": 2,
80
+ "BLOOD_PRESSURE": 40,
81
+ "BLOOD_SUGAR": 51,
82
+ "CLINICAL_FINDINGS": 20,
83
+ "DEMOGRAPHICS": 56,
84
+ "DIAGNOSIS": 30,
85
+ "DOSAGE": 21,
86
+ "DURATION": 26,
87
+ "EXAMINATION": 31,
88
+ "FAMILY_HISTORY": 48,
89
+ "FINDINGS": 45,
90
+ "FOLLOW_UP": 19,
91
+ "FREQUENCY": 32,
92
+ "GENDER": 46,
93
+ "HEART_RATE": 44,
94
+ "IMAGING": 41,
95
+ "LAB_FINDING": 24,
96
+ "LIFESTYLE": 36,
97
+ "MEASUREMENT": 22,
98
+ "MEDICAL_CONDITION": 54,
99
+ "MEDICAL_DEVICE": 49,
100
+ "MEDICAL_EXAM": 18,
101
+ "MEDICAL_HISTORY": 16,
102
+ "MEDICAL_PROCEDURE": 4,
103
+ "MEDICATION": 12,
104
+ "NEXT_VISIT": 25,
105
+ "OBSERVATION": 33,
106
+ "ONSET": 37,
107
+ "OTHER": 1,
108
+ "OTHER_DATES": 52,
109
+ "OUTCOME": 47,
110
+ "PHYSICAL_EXAM": 9,
111
+ "PROCEDURE": 55,
112
+ "PROGNOSIS": 29,
113
+ "PROTECTED_HEALTH_INFORMATION_AGE": 43,
114
+ "PROTECTED_HEALTH_INFORMATION_DATE": 57,
115
+ "PROTECTED_HEALTH_INFORMATION_EMAIL": 5,
116
+ "PROTECTED_HEALTH_INFORMATION_GENDER": 11,
117
+ "PROTECTED_HEALTH_INFORMATION_LOCATION": 58,
118
+ "PROTECTED_HEALTH_INFORMATION_MEDICAL_RECORD": 38,
119
+ "PROTECTED_HEALTH_INFORMATION_NAME": 39,
120
+ "PROTECTED_HEALTH_INFORMATION_PHONE_NUMBER": 23,
121
+ "PROTECTED_HEALTH_INFORMATION_PROFESSION": 8,
122
+ "PULSE": 7,
123
+ "QUANTITY": 27,
124
+ "RECOMMENDATION": 42,
125
+ "REFERRAL": 3,
126
+ "RESPIRATORY_RATE": 53,
127
+ "RISK_FACTOR": 10,
128
+ "SPECIALIST": 50,
129
+ "STAGE": 17,
130
+ "SYMPTOM": 6,
131
+ "TEMPERATURE": 35,
132
+ "TEST": 0,
133
+ "TREATMENT": 14,
134
+ "VITAL_SIGN": 15
135
+ },
136
+ "layer_norm_eps": 1e-12,
137
+ "max_position_embeddings": 512,
138
+ "model_type": "bert",
139
+ "num_attention_heads": 12,
140
+ "num_hidden_layers": 12,
141
+ "pad_token_id": 0,
142
+ "position_embedding_type": "absolute",
143
+ "torch_dtype": "float32",
144
+ "transformers_version": "4.34.1",
145
+ "type_vocab_size": 2,
146
+ "use_cache": true,
147
+ "vocab_size": 128000
148
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f68651a4bf51c2ca194dea412435c356f08d124f7860e625e6bc99ccedffc5
3
+ size 735268201
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[UNK]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[PAD]",
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "max_length": 512,
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
+ "truncation": true,
58
+ "unk_token": "[UNK]"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61fe9f540a399562e56b339c88165467052130e8cac34c208b38c405b444ec90
3
+ size 4091
vocab.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c8eb3d9f7ef0b8f036227785d1dbdc90926ba6816d3899736832d912ccd52e2
3
+ size 1296919