Vrushali commited on
Commit
3b5dcfd
1 Parent(s): c80c53b

Training in progress, epoch 1

Browse files
added_tokens.json CHANGED
@@ -1,30 +1,176 @@
1
  {
2
- "bd": 30524,
3
- "ecg": 30536,
4
- "ekg": 30549,
5
- "elix": 30547,
6
- "gtt": 30548,
7
- "inh": 30543,
8
- "inj": 30539,
9
- "linct": 30546,
10
- "npo": 30528,
11
- "od": 30523,
12
- "oint": 30541,
13
- "otc": 30527,
14
- "pess": 30544,
15
- "prn": 30529,
16
- "q12h": 30535,
17
- "q4h": 30532,
18
- "q6h": 30533,
19
- "q8h": 30534,
20
- "qam": 30530,
21
- "qid": 30526,
22
- "qpm": 30531,
23
- "rx": 30537,
24
- "sos": 30522,
25
- "supp": 30542,
26
- "susp": 30540,
27
- "syrp": 30538,
28
- "tds": 30525,
29
- "xr": 30545
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  }
 
1
  {
2
+ "ACL": 29127,
3
+ "ADH": 29107,
4
+ "ADHD": 28998,
5
+ "ADR": 29019,
6
+ "AFR": 29123,
7
+ "AKA": 29054,
8
+ "ANED": 29077,
9
+ "ARDS": 29155,
10
+ "ARF": 29031,
11
+ "ASCVD": 28997,
12
+ "Administer": 29110,
13
+ "Allow": 29063,
14
+ "Assess": 29060,
15
+ "BKA": 29120,
16
+ "BMP": 29016,
17
+ "BPD": 29163,
18
+ "BSO": 29064,
19
+ "C&S": 29144,
20
+ "CABG": 29017,
21
+ "CDE": 29125,
22
+ "COPD": 29133,
23
+ "CPAP": 29136,
24
+ "CVA": 29021,
25
+ "Conduct": 29036,
26
+ "Confirm": 29092,
27
+ "D&C": 29154,
28
+ "D/C": 29140,
29
+ "DCIS": 29084,
30
+ "DDX": 29156,
31
+ "DJD": 29122,
32
+ "DM": 29048,
33
+ "DNR": 29109,
34
+ "DOE": 29091,
35
+ "DTR": 29141,
36
+ "DVT": 29072,
37
+ "Develop": 29151,
38
+ "Diagnose": 29143,
39
+ "Document": 29113,
40
+ "Drain": 29082,
41
+ "ECG": 29059,
42
+ "ECT": 29139,
43
+ "ETOH": 29138,
44
+ "Elevated": 29078,
45
+ "Evaluate": 29081,
46
+ "Examine": 29070,
47
+ "GOMER": 29166,
48
+ "GvHD": 29097,
49
+ "H&H": 29083,
50
+ "H&P": 29131,
51
+ "HA": 29129,
52
+ "HRT": 29020,
53
+ "I&D": 29134,
54
+ "IBD": 29051,
55
+ "ICD": 29025,
56
+ "ICU": 29132,
57
+ "IM": 29001,
58
+ "IMP": 29112,
59
+ "IPF": 29160,
60
+ "ITU": 29074,
61
+ "IU": 29076,
62
+ "Include": 29085,
63
+ "Infant": 29117,
64
+ "JT": 29088,
65
+ "KCL": 29089,
66
+ "LBP": 29162,
67
+ "LCIS": 29145,
68
+ "LLQ": 29006,
69
+ "LUQ": 29095,
70
+ "M/H": 29050,
71
+ "MCL": 29130,
72
+ "Manage": 29164,
73
+ "N/V": 29159,
74
+ "NBCCS": 29023,
75
+ "NCP": 29126,
76
+ "NPO": 29142,
77
+ "NSR": 29106,
78
+ "O&P": 29124,
79
+ "O.D.": 29121,
80
+ "O.S.": 29100,
81
+ "O.U.": 29103,
82
+ "ORIF": 29032,
83
+ "Obtain": 29037,
84
+ "PCL": 29000,
85
+ "PE": 29043,
86
+ "PERRLA": 29035,
87
+ "PFT": 29057,
88
+ "PMI": 29098,
89
+ "PMS": 29071,
90
+ "PTH": 29069,
91
+ "PTSD": 29055,
92
+ "PUD": 29047,
93
+ "Patient": 29005,
94
+ "Patient's": 29090,
95
+ "Perform": 29009,
96
+ "Plt": 29114,
97
+ "Prescribe": 29030,
98
+ "R/O": 29039,
99
+ "RDS": 29022,
100
+ "REB": 29045,
101
+ "RLQ": 29167,
102
+ "ROS": 29066,
103
+ "RUQ": 29116,
104
+ "Receive": 29040,
105
+ "Refer": 29007,
106
+ "SAD": 29014,
107
+ "SIDS": 29073,
108
+ "SOB": 29099,
109
+ "SQ": 29119,
110
+ "T&A": 29075,
111
+ "TAH": 29029,
112
+ "THR": 29102,
113
+ "TKR": 29044,
114
+ "TMJ": 29105,
115
+ "TSH": 29068,
116
+ "Treat": 29168,
117
+ "UA": 29135,
118
+ "ULN": 29008,
119
+ "URI": 29137,
120
+ "UTI": 29010,
121
+ "Undergo": 29024,
122
+ "VSS": 29087,
123
+ "Wt": 29169,
124
+ "X-ray": 29118,
125
+ "XRT": 28999,
126
+ "a.c.": 29004,
127
+ "a/g": 29157,
128
+ "antiemetic": 29018,
129
+ "anuric": 29104,
130
+ "appendicitis": 29101,
131
+ "b.i.d.": 29111,
132
+ "bandemia": 29046,
133
+ "bedtime": 29086,
134
+ "bibasilar": 29002,
135
+ "bld": 29147,
136
+ "c/o": 29056,
137
+ "chem": 29094,
138
+ "complains": 29033,
139
+ "diagnose": 29061,
140
+ "diagnoses": 29041,
141
+ "dict": 29128,
142
+ "gtt": 29003,
143
+ "h.s.": 29150,
144
+ "h/o": 29079,
145
+ "hormonal": 29058,
146
+ "hypertension": 29067,
147
+ "imbalance": 29161,
148
+ "imbalances": 29080,
149
+ "implantation": 29052,
150
+ "lib": 29065,
151
+ "lytes": 29148,
152
+ "med": 29096,
153
+ "ml": 29158,
154
+ "p.o.": 29053,
155
+ "p.r.n.": 29015,
156
+ "patient's": 29149,
157
+ "p¯": 29165,
158
+ "q.d.": 29034,
159
+ "q.i.d.": 29028,
160
+ "q2h": 29115,
161
+ "q3h": 29152,
162
+ "qAM": 29093,
163
+ "qPM": 29062,
164
+ "qhs": 29153,
165
+ "qod": 29108,
166
+ "s/p": 29049,
167
+ "t.i.d.": 29042,
168
+ "tab": 29146,
169
+ "tenderness": 29013,
170
+ "thyroid": 29027,
171
+ "u/a": 29011,
172
+ "urinary": 29038,
173
+ "ut": 29026,
174
+ "vitro": 28996,
175
+ "vivo": 29012
176
  }
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "samrawal/bert-base-uncased_clinical-ner",
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
@@ -30,5 +30,5 @@
30
  "transformers_version": "4.30.2",
31
  "type_vocab_size": 2,
32
  "use_cache": true,
33
- "vocab_size": 30550
34
  }
 
1
  {
2
+ "_name_or_path": "bert-base-cased",
3
  "architectures": [
4
  "BertForTokenClassification"
5
  ],
 
30
  "transformers_version": "4.30.2",
31
  "type_vocab_size": 2,
32
  "use_cache": true,
33
+ "vocab_size": 29170
34
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41e6d949686ef17570bd2c678e5e51791fce3ebf3ea5b954c4272cbf63b7909c
3
- size 435730925
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c65575a806b93fa6c2717a7ab194b0817ef95d084d48e709e80031a0e62fa0b6
3
+ size 431488749
runs/Jul01_10-54-23_88eb04906cb8/events.out.tfevents.1688208991.88eb04906cb8.24763.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af54040859ed8414f84e73d8975f49b9885a028b068db7d62711b174a8cbaf9
3
+ size 4545
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,11 +1,9 @@
1
  {
2
  "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
4
- "do_basic_tokenize": true,
5
- "do_lower_case": true,
6
  "mask_token": "[MASK]",
7
  "model_max_length": 512,
8
- "never_split": null,
9
  "pad_token": "[PAD]",
10
  "sep_token": "[SEP]",
11
  "strip_accents": null,
 
1
  {
2
  "clean_up_tokenization_spaces": true,
3
  "cls_token": "[CLS]",
4
+ "do_lower_case": false,
 
5
  "mask_token": "[MASK]",
6
  "model_max_length": 512,
 
7
  "pad_token": "[PAD]",
8
  "sep_token": "[SEP]",
9
  "strip_accents": null,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0eaf1768390be3f20f73246c911ee3a8534c518e69aee2a2a92d9aac3d580350
3
  size 3899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bcd05dc8c0d4d8d3017341d0124c49c2629212beae5847a0c2cdfb40540b88e
3
  size 3899
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff