sofia-todeschini
commited on
Commit
•
4f0b61a
1
Parent(s):
e876a70
Training in progress, epoch 0
Browse files- .gitignore +1 -0
- config.json +103 -0
- pytorch_model.bin +3 -0
- runs/Jun25_19-45-13_03aff87f6c59/1719344719.9490438/events.out.tfevents.1719344719.03aff87f6c59.257.1 +3 -0
- runs/Jun25_19-45-13_03aff87f6c59/events.out.tfevents.1719344719.03aff87f6c59.257.0 +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 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dmis-lab/biobert-v1.1",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "Epidemic Forecasting",
|
14 |
+
"1": "Treatment",
|
15 |
+
"2": "Prevention",
|
16 |
+
"3": "Mechanism",
|
17 |
+
"4": "Case Report",
|
18 |
+
"5": "Transmission",
|
19 |
+
"6": "Diagnosis",
|
20 |
+
"7": "Long Covid",
|
21 |
+
"8": "General Info",
|
22 |
+
"9": "Communication",
|
23 |
+
"10": "Contact Tracing",
|
24 |
+
"11": "Drug Targets",
|
25 |
+
"12": "Education",
|
26 |
+
"13": "Effect on Medical Specialties",
|
27 |
+
"14": "Health Policy",
|
28 |
+
"15": "Healthcare Workers",
|
29 |
+
"16": "Imaging",
|
30 |
+
"17": "Immunology",
|
31 |
+
"18": "Inequality",
|
32 |
+
"19": "Medical Devices",
|
33 |
+
"20": "Misinformation",
|
34 |
+
"21": "Model Systems & Tools",
|
35 |
+
"22": "Molecular Biology",
|
36 |
+
"23": "Non-human",
|
37 |
+
"24": "Non-medical",
|
38 |
+
"25": "Pediatrics",
|
39 |
+
"26": "Prevalence",
|
40 |
+
"27": "Psychology",
|
41 |
+
"28": "Recommendations",
|
42 |
+
"29": "Risk Factors",
|
43 |
+
"30": "Surveillance",
|
44 |
+
"31": "Vaccines",
|
45 |
+
"32": "AI/ML/statistics",
|
46 |
+
"33": "Comorbidities",
|
47 |
+
"34": "Telemedicine",
|
48 |
+
"35": "Drug Design and Discovery"
|
49 |
+
},
|
50 |
+
"initializer_range": 0.02,
|
51 |
+
"intermediate_size": 3072,
|
52 |
+
"label2id": {
|
53 |
+
"AI/ML/statistics": 32,
|
54 |
+
"Case Report": 4,
|
55 |
+
"Communication": 9,
|
56 |
+
"Comorbidities": 33,
|
57 |
+
"Contact Tracing": 10,
|
58 |
+
"Diagnosis": 6,
|
59 |
+
"Drug Design and Discovery": 35,
|
60 |
+
"Drug Targets": 11,
|
61 |
+
"Education": 12,
|
62 |
+
"Effect on Medical Specialties": 13,
|
63 |
+
"Epidemic Forecasting": 0,
|
64 |
+
"General Info": 8,
|
65 |
+
"Health Policy": 14,
|
66 |
+
"Healthcare Workers": 15,
|
67 |
+
"Imaging": 16,
|
68 |
+
"Immunology": 17,
|
69 |
+
"Inequality": 18,
|
70 |
+
"Long Covid": 7,
|
71 |
+
"Mechanism": 3,
|
72 |
+
"Medical Devices": 19,
|
73 |
+
"Misinformation": 20,
|
74 |
+
"Model Systems & Tools": 21,
|
75 |
+
"Molecular Biology": 22,
|
76 |
+
"Non-human": 23,
|
77 |
+
"Non-medical": 24,
|
78 |
+
"Pediatrics": 25,
|
79 |
+
"Prevalence": 26,
|
80 |
+
"Prevention": 2,
|
81 |
+
"Psychology": 27,
|
82 |
+
"Recommendations": 28,
|
83 |
+
"Risk Factors": 29,
|
84 |
+
"Surveillance": 30,
|
85 |
+
"Telemedicine": 34,
|
86 |
+
"Transmission": 5,
|
87 |
+
"Treatment": 1,
|
88 |
+
"Vaccines": 31
|
89 |
+
},
|
90 |
+
"layer_norm_eps": 1e-12,
|
91 |
+
"max_position_embeddings": 512,
|
92 |
+
"model_type": "bert",
|
93 |
+
"num_attention_heads": 12,
|
94 |
+
"num_hidden_layers": 12,
|
95 |
+
"pad_token_id": 0,
|
96 |
+
"position_embedding_type": "absolute",
|
97 |
+
"problem_type": "multi_label_classification",
|
98 |
+
"torch_dtype": "float32",
|
99 |
+
"transformers_version": "4.28.0",
|
100 |
+
"type_vocab_size": 2,
|
101 |
+
"use_cache": true,
|
102 |
+
"vocab_size": 28996
|
103 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:246d0adb9a485e523c60dd363db777102daedd5de917195bfe5ccccd093f9dbe
|
3 |
+
size 433425074
|
runs/Jun25_19-45-13_03aff87f6c59/1719344719.9490438/events.out.tfevents.1719344719.03aff87f6c59.257.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d35e2b25f541aeb638c6c4ee8a7fb7483edc6227c3341e0186324b8848964414
|
3 |
+
size 5893
|
runs/Jun25_19-45-13_03aff87f6c59/events.out.tfevents.1719344719.03aff87f6c59.257.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0aeebd02fd35564ce27494e83dc3df84f21b68e0529bca3f9c276e37fbdadb87
|
3 |
+
size 7365
|
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 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": false,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 512,
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"padding": true,
|
11 |
+
"sep_token": "[SEP]",
|
12 |
+
"strip_accents": null,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"truncation": 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:d3ff9b122290e7d48aa26ee82fb5d33513d0cbd6cda905284e4ffd61f10f21ed
|
3 |
+
size 4088
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|