sabousergiu3dan commited on
Commit
f89212a
1 Parent(s): a4c4dd9

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
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": "Agricultural and Biological Sciences",
14
+ "1": "Arts and Humanities",
15
+ "2": "Biochemistry, Genetics and Molecular Biology",
16
+ "3": "Business, Management and Accounting",
17
+ "4": "Chemical Engineering",
18
+ "5": "Chemistry",
19
+ "6": "Computer Science",
20
+ "7": "Decision Sciences",
21
+ "8": "Dentistry",
22
+ "9": "Earth and Planetary Sciences",
23
+ "10": "Economics, Econometrics and Finance",
24
+ "11": "Energy",
25
+ "12": "Engineering",
26
+ "13": "Environmental Science",
27
+ "14": "Immunology and Microbiology",
28
+ "15": "Materials Science",
29
+ "16": "Mathematics",
30
+ "17": "Medicine",
31
+ "18": "Neuroscience",
32
+ "19": "Nursing",
33
+ "20": "Pharmacology, Toxicology and Pharmaceutics",
34
+ "21": "Physics and Astronomy",
35
+ "22": "Psychology",
36
+ "23": "Social Sciences"
37
+ },
38
+ "initializer_range": 0.02,
39
+ "intermediate_size": 3072,
40
+ "label2id": {
41
+ "Agricultural and Biological Sciences": 0,
42
+ "Arts and Humanities": 1,
43
+ "Biochemistry, Genetics and Molecular Biology": 2,
44
+ "Business, Management and Accounting": 3,
45
+ "Chemical Engineering": 4,
46
+ "Chemistry": 5,
47
+ "Computer Science": 6,
48
+ "Decision Sciences": 7,
49
+ "Dentistry": 8,
50
+ "Earth and Planetary Sciences": 9,
51
+ "Economics, Econometrics and Finance": 10,
52
+ "Energy": 11,
53
+ "Engineering": 12,
54
+ "Environmental Science": 13,
55
+ "Immunology and Microbiology": 14,
56
+ "Materials Science": 15,
57
+ "Mathematics": 16,
58
+ "Medicine": 17,
59
+ "Neuroscience": 18,
60
+ "Nursing": 19,
61
+ "Pharmacology, Toxicology and Pharmaceutics": 20,
62
+ "Physics and Astronomy": 21,
63
+ "Psychology": 22,
64
+ "Social Sciences": 23
65
+ },
66
+ "layer_norm_eps": 1e-12,
67
+ "max_position_embeddings": 512,
68
+ "model_type": "bert",
69
+ "num_attention_heads": 12,
70
+ "num_hidden_layers": 12,
71
+ "pad_token_id": 0,
72
+ "position_embedding_type": "absolute",
73
+ "problem_type": "single_label_classification",
74
+ "torch_dtype": "float32",
75
+ "transformers_version": "4.41.2",
76
+ "type_vocab_size": 2,
77
+ "use_cache": true,
78
+ "vocab_size": 30522
79
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fa0feb209077eace242d9f4bb66e7f3a40929de0bd69841ceab4c21dc7207dc
3
+ size 438026320
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 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9815689803ad0e706e3127b991950b86326cf38a18aeb762502ac7efc7516e6c
3
+ size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff