Training in progress, step 25
Browse files- .gitignore +1 -0
- config.json +83 -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 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-disease",
|
14 |
+
"2": "I-disease",
|
15 |
+
"3": "B-body-part",
|
16 |
+
"4": "I-body-part",
|
17 |
+
"5": "B-mutation",
|
18 |
+
"6": "I-mutation",
|
19 |
+
"7": "B-Physiology",
|
20 |
+
"8": "I-Physiology",
|
21 |
+
"9": "B-cohort-patient",
|
22 |
+
"10": "I-cohort-patient",
|
23 |
+
"11": "B-size",
|
24 |
+
"12": "I-size",
|
25 |
+
"13": "B-gender",
|
26 |
+
"14": "I-gender",
|
27 |
+
"15": "B-age",
|
28 |
+
"16": "I-age",
|
29 |
+
"17": "B-Concepts_Ideas",
|
30 |
+
"18": "I-Concepts_Ideas",
|
31 |
+
"19": "B-Disorder",
|
32 |
+
"20": "I-Disorder",
|
33 |
+
"21": "B-gene",
|
34 |
+
"22": "I-gene",
|
35 |
+
"23": "B-Phenomena",
|
36 |
+
"24": "I-Phenomena",
|
37 |
+
"25": "B-ethnicity",
|
38 |
+
"26": "I-ethnicity"
|
39 |
+
},
|
40 |
+
"initializer_range": 0.02,
|
41 |
+
"intermediate_size": 3072,
|
42 |
+
"label2id": {
|
43 |
+
"B-Concepts_Ideas": 17,
|
44 |
+
"B-Disorder": 19,
|
45 |
+
"B-Phenomena": 23,
|
46 |
+
"B-Physiology": 7,
|
47 |
+
"B-age": 15,
|
48 |
+
"B-body-part": 3,
|
49 |
+
"B-cohort-patient": 9,
|
50 |
+
"B-disease": 1,
|
51 |
+
"B-ethnicity": 25,
|
52 |
+
"B-gender": 13,
|
53 |
+
"B-gene": 21,
|
54 |
+
"B-mutation": 5,
|
55 |
+
"B-size": 11,
|
56 |
+
"I-Concepts_Ideas": 18,
|
57 |
+
"I-Disorder": 20,
|
58 |
+
"I-Phenomena": 24,
|
59 |
+
"I-Physiology": 8,
|
60 |
+
"I-age": 16,
|
61 |
+
"I-body-part": 4,
|
62 |
+
"I-cohort-patient": 10,
|
63 |
+
"I-disease": 2,
|
64 |
+
"I-ethnicity": 26,
|
65 |
+
"I-gender": 14,
|
66 |
+
"I-gene": 22,
|
67 |
+
"I-mutation": 6,
|
68 |
+
"I-size": 12,
|
69 |
+
"O": 0
|
70 |
+
},
|
71 |
+
"layer_norm_eps": 1e-12,
|
72 |
+
"max_position_embeddings": 512,
|
73 |
+
"model_type": "bert",
|
74 |
+
"num_attention_heads": 12,
|
75 |
+
"num_hidden_layers": 12,
|
76 |
+
"pad_token_id": 0,
|
77 |
+
"position_embedding_type": "absolute",
|
78 |
+
"torch_dtype": "float32",
|
79 |
+
"transformers_version": "4.27.4",
|
80 |
+
"type_vocab_size": 2,
|
81 |
+
"use_cache": true,
|
82 |
+
"vocab_size": 30522
|
83 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1fb7fab43bf360ace93e5bd50039aeaeb0066d777283b1adfba8bc6829de6d1
|
3 |
+
size 435721773
|
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:a39c65b84c1168b6a63005275795ff52d068229ea00b03c026993456ebe896bf
|
3 |
+
size 3579
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|