sofia-todeschini commited on
Commit
8335870
1 Parent(s): f7a7207

Training in progress, epoch 0

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,105 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedNLP-BiomedBERT-large-uncased-abstract",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_ids": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "Epidemic Forecasting",
15
+ "1": "Treatment",
16
+ "2": "Prevention",
17
+ "3": "Mechanism",
18
+ "4": "Case Report",
19
+ "5": "Transmission",
20
+ "6": "Diagnosis",
21
+ "7": "Long Covid",
22
+ "8": "General Info",
23
+ "9": "Communication",
24
+ "10": "Contact Tracing",
25
+ "11": "Drug Targets",
26
+ "12": "Education",
27
+ "13": "Effect on Medical Specialties",
28
+ "14": "Health Policy",
29
+ "15": "Healthcare Workers",
30
+ "16": "Imaging",
31
+ "17": "Immunology",
32
+ "18": "Inequality",
33
+ "19": "Medical Devices",
34
+ "20": "Misinformation",
35
+ "21": "Model Systems & Tools",
36
+ "22": "Molecular Biology",
37
+ "23": "Non-human",
38
+ "24": "Non-medical",
39
+ "25": "Pediatrics",
40
+ "26": "Prevalence",
41
+ "27": "Psychology",
42
+ "28": "Recommendations",
43
+ "29": "Risk Factors",
44
+ "30": "Surveillance",
45
+ "31": "Vaccines",
46
+ "32": "AI/ML/statistics",
47
+ "33": "Comorbidities",
48
+ "34": "Telemedicine",
49
+ "35": "Drug Design and Discovery"
50
+ },
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 4096,
53
+ "label2id": {
54
+ "AI/ML/statistics": 32,
55
+ "Case Report": 4,
56
+ "Communication": 9,
57
+ "Comorbidities": 33,
58
+ "Contact Tracing": 10,
59
+ "Diagnosis": 6,
60
+ "Drug Design and Discovery": 35,
61
+ "Drug Targets": 11,
62
+ "Education": 12,
63
+ "Effect on Medical Specialties": 13,
64
+ "Epidemic Forecasting": 0,
65
+ "General Info": 8,
66
+ "Health Policy": 14,
67
+ "Healthcare Workers": 15,
68
+ "Imaging": 16,
69
+ "Immunology": 17,
70
+ "Inequality": 18,
71
+ "Long Covid": 7,
72
+ "Mechanism": 3,
73
+ "Medical Devices": 19,
74
+ "Misinformation": 20,
75
+ "Model Systems & Tools": 21,
76
+ "Molecular Biology": 22,
77
+ "Non-human": 23,
78
+ "Non-medical": 24,
79
+ "Pediatrics": 25,
80
+ "Prevalence": 26,
81
+ "Prevention": 2,
82
+ "Psychology": 27,
83
+ "Recommendations": 28,
84
+ "Risk Factors": 29,
85
+ "Surveillance": 30,
86
+ "Telemedicine": 34,
87
+ "Transmission": 5,
88
+ "Treatment": 1,
89
+ "Vaccines": 31
90
+ },
91
+ "layer_norm_eps": 1e-12,
92
+ "max_position_embeddings": 512,
93
+ "model_type": "bert",
94
+ "num_attention_heads": 16,
95
+ "num_hidden_layers": 24,
96
+ "output_past": true,
97
+ "pad_token_id": 0,
98
+ "position_embedding_type": "absolute",
99
+ "problem_type": "multi_label_classification",
100
+ "torch_dtype": "float32",
101
+ "transformers_version": "4.28.0",
102
+ "type_vocab_size": 2,
103
+ "use_cache": true,
104
+ "vocab_size": 30522
105
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6397a1f8bb6fc8406c09a836e091ac980e4a3bf8cd744da92b71ac66cfd6e88
3
+ size 1340854450
runs/Jun25_21-22-14_a6f3f0bbdd1c/1719350540.2760277/events.out.tfevents.1719350540.a6f3f0bbdd1c.695.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a8f9bf7dd0ec6a52d539c8708b16e43df70885902029e9be97f4612052d59dd
3
+ size 5920
runs/Jun25_21-22-14_a6f3f0bbdd1c/events.out.tfevents.1719350540.a6f3f0bbdd1c.695.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78dc366b86bf3c99c73e38d1ba91edc819594d47d19729bbf91e53fd7d5d4a6c
3
+ size 7460
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": true,
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 sha256:8fcf789e4aec35b15fcf434de4513ef30314a26ac4594056a357e841f54150f0
3
+ size 4088
vocab.txt ADDED
The diff for this file is too large to render. See raw diff