Done
Browse files- .gitignore +1 -0
- config.json +95 -0
- pytorch_model.bin +3 -0
- runs/Jul11_10-45-15_87a95fb9f6c9/1657536394.7879772/events.out.tfevents.1657536394.87a95fb9f6c9.76.1 +3 -0
- runs/Jul11_10-45-15_87a95fb9f6c9/events.out.tfevents.1657536394.87a95fb9f6c9.76.0 +3 -0
- runs/Jul11_11-05-10_87a95fb9f6c9/1657537539.358535/events.out.tfevents.1657537539.87a95fb9f6c9.76.3 +3 -0
- runs/Jul11_11-05-10_87a95fb9f6c9/events.out.tfevents.1657537539.87a95fb9f6c9.76.2 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,95 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "I-Gene_or_gene_product",
|
15 |
+
"3": "B-Cancer",
|
16 |
+
"4": "I-Cancer",
|
17 |
+
"5": "B-Cell",
|
18 |
+
"6": "I-Cell",
|
19 |
+
"7": "B-Organism",
|
20 |
+
"8": "B-Simple_chemical",
|
21 |
+
"9": "I-Simple_chemical",
|
22 |
+
"10": "B-Multi-tissue_structure",
|
23 |
+
"11": "I-Multi-tissue_structure",
|
24 |
+
"12": "B-Organ",
|
25 |
+
"13": "B-Organism_subdivision",
|
26 |
+
"14": "B-Tissue",
|
27 |
+
"15": "I-Tissue",
|
28 |
+
"16": "B-Immaterial_anatomical_entity",
|
29 |
+
"17": "B-Organism_substance",
|
30 |
+
"18": "I-Organism_substance",
|
31 |
+
"19": "I-Organism",
|
32 |
+
"20": "I-Organism_subdivision",
|
33 |
+
"21": "B-Cellular_component",
|
34 |
+
"22": "I-Immaterial_anatomical_entity",
|
35 |
+
"23": "I-Cellular_component",
|
36 |
+
"24": "B-Pathological_formation",
|
37 |
+
"25": "I-Pathological_formation",
|
38 |
+
"26": "I-Organ",
|
39 |
+
"27": "B-Amino_acid",
|
40 |
+
"28": "I-Amino_acid",
|
41 |
+
"29": "B-Anatomical_system",
|
42 |
+
"30": "I-Anatomical_system",
|
43 |
+
"31": "B-Developing_anatomical_structure",
|
44 |
+
"32": "I-Developing_anatomical_structure"
|
45 |
+
},
|
46 |
+
"initializer_range": 0.02,
|
47 |
+
"intermediate_size": 3072,
|
48 |
+
"label2id": {
|
49 |
+
"B-Amino_acid": 27,
|
50 |
+
"B-Anatomical_system": 29,
|
51 |
+
"B-Cancer": 3,
|
52 |
+
"B-Cell": 5,
|
53 |
+
"B-Cellular_component": 21,
|
54 |
+
"B-Developing_anatomical_structure": 31,
|
55 |
+
"B-Gene_or_gene_product": 1,
|
56 |
+
"B-Immaterial_anatomical_entity": 16,
|
57 |
+
"B-Multi-tissue_structure": 10,
|
58 |
+
"B-Organ": 12,
|
59 |
+
"B-Organism": 7,
|
60 |
+
"B-Organism_subdivision": 13,
|
61 |
+
"B-Organism_substance": 17,
|
62 |
+
"B-Pathological_formation": 24,
|
63 |
+
"B-Simple_chemical": 8,
|
64 |
+
"B-Tissue": 14,
|
65 |
+
"I-Amino_acid": 28,
|
66 |
+
"I-Anatomical_system": 30,
|
67 |
+
"I-Cancer": 4,
|
68 |
+
"I-Cell": 6,
|
69 |
+
"I-Cellular_component": 23,
|
70 |
+
"I-Developing_anatomical_structure": 32,
|
71 |
+
"I-Gene_or_gene_product": 2,
|
72 |
+
"I-Immaterial_anatomical_entity": 22,
|
73 |
+
"I-Multi-tissue_structure": 11,
|
74 |
+
"I-Organ": 26,
|
75 |
+
"I-Organism": 19,
|
76 |
+
"I-Organism_subdivision": 20,
|
77 |
+
"I-Organism_substance": 18,
|
78 |
+
"I-Pathological_formation": 25,
|
79 |
+
"I-Simple_chemical": 9,
|
80 |
+
"I-Tissue": 15,
|
81 |
+
"O": 0
|
82 |
+
},
|
83 |
+
"layer_norm_eps": 1e-12,
|
84 |
+
"max_position_embeddings": 512,
|
85 |
+
"model_type": "bert",
|
86 |
+
"num_attention_heads": 12,
|
87 |
+
"num_hidden_layers": 12,
|
88 |
+
"pad_token_id": 0,
|
89 |
+
"position_embedding_type": "absolute",
|
90 |
+
"torch_dtype": "float32",
|
91 |
+
"transformers_version": "4.20.1",
|
92 |
+
"type_vocab_size": 2,
|
93 |
+
"use_cache": true,
|
94 |
+
"vocab_size": 28996
|
95 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:829571053ea9c416ba76a1ee69094fa32c3df17f7625cacb3127d26a07a9c35e
|
3 |
+
size 431050673
|
runs/Jul11_10-45-15_87a95fb9f6c9/1657536394.7879772/events.out.tfevents.1657536394.87a95fb9f6c9.76.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cd9d482167f93e4283f7864d113168c05fbea84992d37783f3a48f2f16f125d
|
3 |
+
size 5317
|
runs/Jul11_10-45-15_87a95fb9f6c9/events.out.tfevents.1657536394.87a95fb9f6c9.76.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:767d37b9e62980497446ab85a5c8ee5276926850a3b61f2d9e56488519f3f909
|
3 |
+
size 7307
|
runs/Jul11_11-05-10_87a95fb9f6c9/1657537539.358535/events.out.tfevents.1657537539.87a95fb9f6c9.76.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b85b2f719ce576d8f2fb81341252bb4cb9f939b9eb44d46f15ef290545fa0a5a
|
3 |
+
size 5317
|
runs/Jul11_11-05-10_87a95fb9f6c9/events.out.tfevents.1657537539.87a95fb9f6c9.76.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec69c3643f6443d19b3ec2385b1e41651939260fe176f9ae3247b3d56f8a97b5
|
3 |
+
size 10626
|
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 sha256:7aec1da95bf0c604f799d78370626641d2b5cf097f7b560d54755e2d74726adf
|
3 |
+
size 3311
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|