Training in progress, step 25
Browse files- .gitignore +1 -0
- config.json +111 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
|
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_Protein",
|
14 |
+
"2": "I-Gene_Protein",
|
15 |
+
"3": "B-DNAMutation",
|
16 |
+
"4": "I-DNAMutation",
|
17 |
+
"5": "B-ProteinMutation",
|
18 |
+
"6": "I-ProteinMutation",
|
19 |
+
"7": "B-SNP",
|
20 |
+
"8": "I-SNP",
|
21 |
+
"9": "B-DNA_modification",
|
22 |
+
"10": "I-DNA_modification",
|
23 |
+
"11": "B-RNA",
|
24 |
+
"12": "I-RNA",
|
25 |
+
"13": "B-RNA_Mutation",
|
26 |
+
"14": "I-RNA_Mutation",
|
27 |
+
"15": "B-locus",
|
28 |
+
"16": "I-locus",
|
29 |
+
"17": "B-disease",
|
30 |
+
"18": "I-disease",
|
31 |
+
"19": "B-body-part",
|
32 |
+
"20": "I-body-part",
|
33 |
+
"21": "B-mutation",
|
34 |
+
"22": "I-mutation",
|
35 |
+
"23": "B-Physiology",
|
36 |
+
"24": "I-Physiology",
|
37 |
+
"25": "B-cohort-patient",
|
38 |
+
"26": "I-cohort-patient",
|
39 |
+
"27": "B-size",
|
40 |
+
"28": "I-size",
|
41 |
+
"29": "B-gender",
|
42 |
+
"30": "I-gender",
|
43 |
+
"31": "B-age",
|
44 |
+
"32": "I-age",
|
45 |
+
"33": "B-Concepts_Ideas",
|
46 |
+
"34": "I-Concepts_Ideas",
|
47 |
+
"35": "B-Disorder",
|
48 |
+
"36": "I-Disorder",
|
49 |
+
"37": "B-Phenomena",
|
50 |
+
"38": "I-Phenomena",
|
51 |
+
"39": "B-ethnicity",
|
52 |
+
"40": "I-ethnicity"
|
53 |
+
},
|
54 |
+
"initializer_range": 0.02,
|
55 |
+
"intermediate_size": 3072,
|
56 |
+
"label2id": {
|
57 |
+
"B-Concepts_Ideas": 33,
|
58 |
+
"B-DNAMutation": 3,
|
59 |
+
"B-DNA_modification": 9,
|
60 |
+
"B-Disorder": 35,
|
61 |
+
"B-Gene_Protein": 1,
|
62 |
+
"B-Phenomena": 37,
|
63 |
+
"B-Physiology": 23,
|
64 |
+
"B-ProteinMutation": 5,
|
65 |
+
"B-RNA": 11,
|
66 |
+
"B-RNA_Mutation": 13,
|
67 |
+
"B-SNP": 7,
|
68 |
+
"B-age": 31,
|
69 |
+
"B-body-part": 19,
|
70 |
+
"B-cohort-patient": 25,
|
71 |
+
"B-disease": 17,
|
72 |
+
"B-ethnicity": 39,
|
73 |
+
"B-gender": 29,
|
74 |
+
"B-locus": 15,
|
75 |
+
"B-mutation": 21,
|
76 |
+
"B-size": 27,
|
77 |
+
"I-Concepts_Ideas": 34,
|
78 |
+
"I-DNAMutation": 4,
|
79 |
+
"I-DNA_modification": 10,
|
80 |
+
"I-Disorder": 36,
|
81 |
+
"I-Gene_Protein": 2,
|
82 |
+
"I-Phenomena": 38,
|
83 |
+
"I-Physiology": 24,
|
84 |
+
"I-ProteinMutation": 6,
|
85 |
+
"I-RNA": 12,
|
86 |
+
"I-RNA_Mutation": 14,
|
87 |
+
"I-SNP": 8,
|
88 |
+
"I-age": 32,
|
89 |
+
"I-body-part": 20,
|
90 |
+
"I-cohort-patient": 26,
|
91 |
+
"I-disease": 18,
|
92 |
+
"I-ethnicity": 40,
|
93 |
+
"I-gender": 30,
|
94 |
+
"I-locus": 16,
|
95 |
+
"I-mutation": 22,
|
96 |
+
"I-size": 28,
|
97 |
+
"O": 0
|
98 |
+
},
|
99 |
+
"layer_norm_eps": 1e-12,
|
100 |
+
"max_position_embeddings": 512,
|
101 |
+
"model_type": "bert",
|
102 |
+
"num_attention_heads": 12,
|
103 |
+
"num_hidden_layers": 12,
|
104 |
+
"pad_token_id": 0,
|
105 |
+
"position_embedding_type": "absolute",
|
106 |
+
"torch_dtype": "float32",
|
107 |
+
"transformers_version": "4.27.4",
|
108 |
+
"type_vocab_size": 2,
|
109 |
+
"use_cache": true,
|
110 |
+
"vocab_size": 30522
|
111 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df8c14fd414bc974ab8e46a794adaaeac714ec24d5e9d31adb941bc13082b2de
|
3 |
+
size 435764845
|
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 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": true,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_len": 512,
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": null,
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"trunction": true,
|
16 |
+
"unk_token": "[UNK]"
|
17 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6cb316a901a5abc2b055dc790c1ee5cd6158112ac126f66a18de882ade97c38
|
3 |
+
size 3579
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|