sofia-todeschini commited on
Commit
e302aa4
·
1 Parent(s): b6daa92

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-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
+ },
47
+ "initializer_range": 0.02,
48
+ "intermediate_size": 4096,
49
+ "label2id": {
50
+ "Case Report": 4,
51
+ "Communication": 9,
52
+ "Contact Tracing": 10,
53
+ "Diagnosis": 6,
54
+ "Drug Targets": 11,
55
+ "Education": 12,
56
+ "Effect on Medical Specialties": 13,
57
+ "Epidemic Forecasting": 0,
58
+ "General Info": 8,
59
+ "Health Policy": 14,
60
+ "Healthcare Workers": 15,
61
+ "Imaging": 16,
62
+ "Immunology": 17,
63
+ "Inequality": 18,
64
+ "Long Covid": 7,
65
+ "Mechanism": 3,
66
+ "Medical Devices": 19,
67
+ "Misinformation": 20,
68
+ "Model Systems & Tools": 21,
69
+ "Molecular Biology": 22,
70
+ "Non-human": 23,
71
+ "Non-medical": 24,
72
+ "Pediatrics": 25,
73
+ "Prevalence": 26,
74
+ "Prevention": 2,
75
+ "Psychology": 27,
76
+ "Recommendations": 28,
77
+ "Risk Factors": 29,
78
+ "Surveillance": 30,
79
+ "Transmission": 5,
80
+ "Treatment": 1,
81
+ "Vaccines": 31
82
+ },
83
+ "layer_norm_eps": 1e-12,
84
+ "max_position_embeddings": 512,
85
+ "model_type": "bert",
86
+ "num_attention_heads": 16,
87
+ "num_hidden_layers": 24,
88
+ "output_past": true,
89
+ "pad_token_id": 0,
90
+ "position_embedding_type": "absolute",
91
+ "problem_type": "multi_label_classification",
92
+ "torch_dtype": "float32",
93
+ "transformers_version": "4.28.0",
94
+ "type_vocab_size": 2,
95
+ "use_cache": true,
96
+ "vocab_size": 30522
97
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ffa3a6f90e37d15a56405fbf355543d211e2f514e1bdbf49918e20ad86d1314
3
+ size 1340837621
runs/Nov01_09-39-14_c0315f06a351/1698831559.8933997/events.out.tfevents.1698831559.c0315f06a351.32.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fea0d6af80c971c881829f892e928b91ff8b2547ae3588b8591158f03af5c868
3
+ size 5934
runs/Nov01_09-39-14_c0315f06a351/events.out.tfevents.1698831559.c0315f06a351.32.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e6c6b05478c659b7a8313ed5b68bee03c5217713fe2d2770552ac45e725f018
3
+ size 9755
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 sha256:057171dab30b1fb8ad0db7a45162d5163f1251a82df026a438e756d26d27a56b
3
+ size 3643
vocab.txt ADDED
The diff for this file is too large to render. See raw diff