ericntay commited on
Commit
182c79b
1 Parent(s): 7dd1ad0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "emilyalsentzer/Bio_ClinicalBERT",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-Gene_or_gene_product",
14
+ "2": "B-Cell",
15
+ "3": "I-Cell",
16
+ "4": "I-Gene_or_gene_product",
17
+ "5": "B-Cancer",
18
+ "6": "I-Cancer",
19
+ "7": "B-Organ",
20
+ "8": "I-Organ"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "B-Cancer": 5,
26
+ "B-Cell": 2,
27
+ "B-Gene_or_gene_product": 1,
28
+ "B-Organ": 7,
29
+ "I-Cancer": 6,
30
+ "I-Cell": 3,
31
+ "I-Gene_or_gene_product": 4,
32
+ "I-Organ": 8,
33
+ "O": 0
34
+ },
35
+ "layer_norm_eps": 1e-12,
36
+ "max_position_embeddings": 512,
37
+ "model_type": "bert",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "pad_token_id": 0,
41
+ "position_embedding_type": "absolute",
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.22.2",
44
+ "type_vocab_size": 2,
45
+ "use_cache": true,
46
+ "vocab_size": 28996
47
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08f1c60f8bab9f6cfb5d68f64da523946c72a7c4b58e0c5e22054233e4fd1087
3
+ size 430976817
runs/Sep30_16-22-57_024dfcdc8d78/1664554988.6383555/events.out.tfevents.1664554988.024dfcdc8d78.66.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f68b76f090422cd5e3c50f9c51bc95c40f19d3e424736d4806472fa7e0dd284
3
+ size 5522
runs/Sep30_16-22-57_024dfcdc8d78/events.out.tfevents.1664554988.024dfcdc8d78.66.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f88662cf60b0f481078e0f06b81a0188bea3a771935d9eb26176fbed911bba0
3
+ size 10120
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "name_or_path": "emilyalsentzer/Bio_ClinicalBERT",
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": null,
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c21f2100d0d8e4354408b4e3ff3d3acfaf84b3fead914cfe80b9af4e1dd520a
3
+ size 3375
vocab.txt ADDED
The diff for this file is too large to render. See raw diff