sofia-todeschini commited on
Commit
940912b
1 Parent(s): 172b6b1

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kamalkraj/bioelectra-base-discriminator-pubmed",
3
+ "architectures": [
4
+ "ElectraForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
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
+ },
46
+ "initializer_range": 0.02,
47
+ "intermediate_size": 3072,
48
+ "label2id": {
49
+ "Case Report": 4,
50
+ "Communication": 9,
51
+ "Contact Tracing": 10,
52
+ "Diagnosis": 6,
53
+ "Drug Targets": 11,
54
+ "Education": 12,
55
+ "Effect on Medical Specialties": 13,
56
+ "Epidemic Forecasting": 0,
57
+ "General Info": 8,
58
+ "Health Policy": 14,
59
+ "Healthcare Workers": 15,
60
+ "Imaging": 16,
61
+ "Immunology": 17,
62
+ "Inequality": 18,
63
+ "Long Covid": 7,
64
+ "Mechanism": 3,
65
+ "Medical Devices": 19,
66
+ "Misinformation": 20,
67
+ "Model Systems & Tools": 21,
68
+ "Molecular Biology": 22,
69
+ "Non-human": 23,
70
+ "Non-medical": 24,
71
+ "Pediatrics": 25,
72
+ "Prevalence": 26,
73
+ "Prevention": 2,
74
+ "Psychology": 27,
75
+ "Recommendations": 28,
76
+ "Risk Factors": 29,
77
+ "Surveillance": 30,
78
+ "Transmission": 5,
79
+ "Treatment": 1,
80
+ "Vaccines": 31
81
+ },
82
+ "layer_norm_eps": 1e-12,
83
+ "max_position_embeddings": 512,
84
+ "model_type": "electra",
85
+ "num_attention_heads": 12,
86
+ "num_hidden_layers": 12,
87
+ "pad_token_id": 0,
88
+ "position_embedding_type": "absolute",
89
+ "problem_type": "multi_label_classification",
90
+ "summary_activation": "gelu",
91
+ "summary_last_dropout": 0.1,
92
+ "summary_type": "first",
93
+ "summary_use_proj": true,
94
+ "torch_dtype": "float32",
95
+ "transformers_version": "4.28.0",
96
+ "type_vocab_size": 2,
97
+ "use_cache": true,
98
+ "vocab_size": 30522
99
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe34cd961aebc881349dd9acb2649a5338f45bca0c3b0ff6171e8d21a086e021
3
+ size 438101298
runs/Mar11_19-30-29_5c78c68bac9f/1710185476.3363593/events.out.tfevents.1710185476.5c78c68bac9f.176.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a0b442c5d992cb1a9cec540eae0d58c7ab2177d441eca82087f84948771451d
3
+ size 5908
runs/Mar11_19-30-29_5c78c68bac9f/events.out.tfevents.1710185476.5c78c68bac9f.176.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55d29b82d20d7aaf43da95e71b7cd441ff68ee5dfb6f11e538e5f9ea63e52d24
3
+ size 7167
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": "ElectraTokenizer",
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 sha256:98201eb1468d14360380ddcfe48bc57b80bae75304ebc551d12d60deb0c583cc
3
+ size 4088
vocab.txt ADDED
The diff for this file is too large to render. See raw diff