Training in progress, epoch 1
Browse files- .gitignore +1 -0
- added_tokens.json +187 -0
- config.json +35 -0
- pytorch_model.bin +3 -0
- runs/Jul03_15-02-00_b2c3a7d6d051/events.out.tfevents.1688396525.b2c3a7d6d051.214.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
added_tokens.json
ADDED
@@ -0,0 +1,187 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
" test": 29069,
|
3 |
+
"a.c.": 29021,
|
4 |
+
"a/g": 29066,
|
5 |
+
"ac": 29125,
|
6 |
+
"acl": 29045,
|
7 |
+
"ad-lib": 29055,
|
8 |
+
"adh": 29003,
|
9 |
+
"adhd": 29059,
|
10 |
+
"adr": 29119,
|
11 |
+
"afr": 29004,
|
12 |
+
"aned": 29163,
|
13 |
+
"anemia": 29060,
|
14 |
+
"antiemetic": 29144,
|
15 |
+
"anuric": 29149,
|
16 |
+
"appendicitis": 29012,
|
17 |
+
"ards": 29111,
|
18 |
+
"arf": 29178,
|
19 |
+
"ascvd": 29075,
|
20 |
+
"b.i.d.": 29002,
|
21 |
+
"bandemia": 29109,
|
22 |
+
"bedtime": 29158,
|
23 |
+
"bibasilar": 29151,
|
24 |
+
"bka": 29023,
|
25 |
+
"bld": 29167,
|
26 |
+
"bmp": 29067,
|
27 |
+
"bp": 29044,
|
28 |
+
"bpd": 29043,
|
29 |
+
"bsl": 29033,
|
30 |
+
"bso": 29073,
|
31 |
+
"c&s": 29170,
|
32 |
+
"c/o": 29028,
|
33 |
+
"cabg": 29011,
|
34 |
+
"cbc": 29161,
|
35 |
+
"cde": 29049,
|
36 |
+
"chem": 29039,
|
37 |
+
"chemotherapy": 29164,
|
38 |
+
"complains": 29079,
|
39 |
+
"copd": 29018,
|
40 |
+
"cpap": 29080,
|
41 |
+
"cr": 29086,
|
42 |
+
"ct": 29112,
|
43 |
+
"cva": 29084,
|
44 |
+
"d&c": 29168,
|
45 |
+
"d/c": 29153,
|
46 |
+
"dc": 29174,
|
47 |
+
"dcis": 29131,
|
48 |
+
"ddx": 29099,
|
49 |
+
"diagnose": 29025,
|
50 |
+
"diagnoses": 29177,
|
51 |
+
"dict": 29041,
|
52 |
+
"djd": 29179,
|
53 |
+
"dm": 29133,
|
54 |
+
"dnc": 29103,
|
55 |
+
"dnr": 29088,
|
56 |
+
"doe": 29024,
|
57 |
+
"dtr": 29050,
|
58 |
+
"dvt": 29051,
|
59 |
+
"ecg": 29115,
|
60 |
+
"ect": 29031,
|
61 |
+
"eeg": 29063,
|
62 |
+
"etoh": 29037,
|
63 |
+
"fx": 29108,
|
64 |
+
"gomer": 29096,
|
65 |
+
"gtt": 29054,
|
66 |
+
"gvhd": 29032,
|
67 |
+
"h&h": 29127,
|
68 |
+
"h&p": 29087,
|
69 |
+
"h.s.": 29147,
|
70 |
+
"h/o": 29047,
|
71 |
+
"hba1c": 29082,
|
72 |
+
"hormonal": 29130,
|
73 |
+
"hrt": 29094,
|
74 |
+
"hs": 29180,
|
75 |
+
"hypertension": 29129,
|
76 |
+
"i&d": 29113,
|
77 |
+
"ibd": 29077,
|
78 |
+
"icd": 29034,
|
79 |
+
"icu": 29146,
|
80 |
+
"imbalance": 29030,
|
81 |
+
"imbalances": 28997,
|
82 |
+
"implantation": 29173,
|
83 |
+
"instill": 29128,
|
84 |
+
"ipf": 29010,
|
85 |
+
"itu": 29150,
|
86 |
+
"iu": 29042,
|
87 |
+
"iv": 29000,
|
88 |
+
"jt": 29091,
|
89 |
+
"kcl": 29013,
|
90 |
+
"lbp": 29056,
|
91 |
+
"lcis": 29107,
|
92 |
+
"llq": 29105,
|
93 |
+
"luq": 29141,
|
94 |
+
"lytes": 29154,
|
95 |
+
"m/h": 29040,
|
96 |
+
"mcl": 29176,
|
97 |
+
"med": 29143,
|
98 |
+
"ml": 29145,
|
99 |
+
"mri": 29137,
|
100 |
+
"mvp": 29062,
|
101 |
+
"n/v": 29121,
|
102 |
+
"nbccs": 29036,
|
103 |
+
"nbm": 29001,
|
104 |
+
"ncp": 29038,
|
105 |
+
"npo": 29068,
|
106 |
+
"nsr": 29165,
|
107 |
+
"o&p": 29092,
|
108 |
+
"od": 29148,
|
109 |
+
"orif": 29142,
|
110 |
+
"os.": 29159,
|
111 |
+
"ou.": 29061,
|
112 |
+
"p.o.": 29171,
|
113 |
+
"p.r.n.": 29048,
|
114 |
+
"patient's": 29020,
|
115 |
+
"pc": 29009,
|
116 |
+
"pcl": 29140,
|
117 |
+
"pd": 29101,
|
118 |
+
"pe": 29160,
|
119 |
+
"perrla": 29035,
|
120 |
+
"pft": 29134,
|
121 |
+
"plt": 28998,
|
122 |
+
"pmi": 29135,
|
123 |
+
"pms": 29064,
|
124 |
+
"pr": 29005,
|
125 |
+
"prescribe": 29078,
|
126 |
+
"prn": 29152,
|
127 |
+
"pt": 29065,
|
128 |
+
"pth": 29016,
|
129 |
+
"ptsd": 29116,
|
130 |
+
"ptt": 29008,
|
131 |
+
"pud": 29104,
|
132 |
+
"p¯": 29120,
|
133 |
+
"q.d.": 29155,
|
134 |
+
"q.i.d.": 29052,
|
135 |
+
"q2h": 29022,
|
136 |
+
"q3h": 29124,
|
137 |
+
"qam": 29014,
|
138 |
+
"qhs": 29015,
|
139 |
+
"qod": 29157,
|
140 |
+
"qpm": 29172,
|
141 |
+
"r/o": 29017,
|
142 |
+
"ra": 29175,
|
143 |
+
"rbs": 29114,
|
144 |
+
"rds": 29074,
|
145 |
+
"reb": 28999,
|
146 |
+
"rectum": 29117,
|
147 |
+
"reflexes": 29098,
|
148 |
+
"relievers": 29123,
|
149 |
+
"rlq": 29095,
|
150 |
+
"ros": 29162,
|
151 |
+
"ruq": 29110,
|
152 |
+
"s/p": 29097,
|
153 |
+
"sc": 29169,
|
154 |
+
"sids": 29081,
|
155 |
+
"sos": 29132,
|
156 |
+
"sr": 29046,
|
157 |
+
"stat": 29070,
|
158 |
+
"subcutaneous": 29053,
|
159 |
+
"symptom ": 29083,
|
160 |
+
"t&a": 29027,
|
161 |
+
"t.i.d.": 29100,
|
162 |
+
"tab": 29029,
|
163 |
+
"tah": 29166,
|
164 |
+
"tenderness": 29122,
|
165 |
+
"thr": 29138,
|
166 |
+
"thyroid": 29139,
|
167 |
+
"tkr": 29090,
|
168 |
+
"tmj": 29156,
|
169 |
+
"tsh": 29057,
|
170 |
+
"u/a": 29106,
|
171 |
+
"ua": 29058,
|
172 |
+
"uln": 29007,
|
173 |
+
"ultrasound": 29071,
|
174 |
+
"uri": 29089,
|
175 |
+
"urinary": 29072,
|
176 |
+
"usg": 29026,
|
177 |
+
"ut": 29076,
|
178 |
+
"uti": 29118,
|
179 |
+
"vitro": 28996,
|
180 |
+
"vivo": 29093,
|
181 |
+
"vss": 29006,
|
182 |
+
"wt": 29085,
|
183 |
+
"x-r": 29019,
|
184 |
+
"x-ray": 29102,
|
185 |
+
"xr": 29126,
|
186 |
+
"xrt": 29136
|
187 |
+
}
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dslim/bert-base-NER",
|
3 |
+
"_num_labels": 9,
|
4 |
+
"architectures": [
|
5 |
+
"BertForTokenClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "ABV"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"ABV": 1,
|
20 |
+
"O": 0
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-12,
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"model_type": "bert",
|
25 |
+
"num_attention_heads": 12,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"output_past": true,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.30.2",
|
32 |
+
"type_vocab_size": 2,
|
33 |
+
"use_cache": true,
|
34 |
+
"vocab_size": 29181
|
35 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e074f705e951d5894303f468611c9e2e717da1514fc60fb5cb0d05a7a93f136
|
3 |
+
size 431525357
|
runs/Jul03_15-02-00_b2c3a7d6d051/events.out.tfevents.1688396525.b2c3a7d6d051.214.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d536f9289fe6baa37e9d4d17c984a1fb29896d3066ebc2474a0335ec46583e95
|
3 |
+
size 4604
|
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 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": false,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"max_len": 512,
|
8 |
+
"model_max_length": 512,
|
9 |
+
"never_split": null,
|
10 |
+
"pad_token": "[PAD]",
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa0f19e7791f63d36255053d2755af728f2553ba6c5a4e6febcd7796b326f618
|
3 |
+
size 3963
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|