ericntay commited on
Commit
7f99aca
1 Parent(s): 422e63c
.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": "B-Cancer",
13
+ "1": "O",
14
+ "2": "B-Cell",
15
+ "3": "I-Cell",
16
+ "4": "B-Organ",
17
+ "5": "B-Gene_or_gene_product",
18
+ "6": "I-Gene_or_gene_product",
19
+ "7": "I-Cancer",
20
+ "8": "I-Organ"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "B-Cancer": 0,
26
+ "B-Cell": 2,
27
+ "B-Gene_or_gene_product": 5,
28
+ "B-Organ": 4,
29
+ "I-Cancer": 7,
30
+ "I-Cell": 3,
31
+ "I-Gene_or_gene_product": 6,
32
+ "I-Organ": 8,
33
+ "O": 1
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": "4.22.1",
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 sha256:7ab5d6a7b55d958ac5b63de467bb63a8d3da9436337776cbd4f112dbdb48811a
3
+ size 430976817
runs/Sep23_19-50-06_bf668db1ef65/1663962615.4751086/events.out.tfevents.1663962615.bf668db1ef65.239.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c23309e34662d73bbdf6f7f410b323524b75ff704a46c1a45f0a1afb3735f1b
3
+ size 5522
runs/Sep23_19-50-06_bf668db1ef65/events.out.tfevents.1663962615.bf668db1ef65.239.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f34f954b6feb212a4cf62d5026667f8113cc9a2f9338b19d4bb768c4a2007214
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:f8a3c714dbec38c92e4ec4e84a745e8645ea0117f42318b97d65d3a69432b354
3
+ size 3375
vocab.txt ADDED
The diff for this file is too large to render. See raw diff