Mukalingam0813 commited on
Commit
d6136c6
·
verified ·
1 Parent(s): 56bc9a9

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert/distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Pornography",
13
+ "1": "Erotica",
14
+ "2": "Adult Content",
15
+ "3": "Crime",
16
+ "4": "Sexual Assault",
17
+ "5": "Violent Crime",
18
+ "6": "Terrorist Attacks",
19
+ "7": "Counterterrorism",
20
+ "8": "Smoking",
21
+ "9": "Vaping",
22
+ "10": "Tobacco Use",
23
+ "11": "Military Conflict",
24
+ "12": "War",
25
+ "13": "International Relations",
26
+ "14": "Pandemic",
27
+ "15": "Vaccines",
28
+ "16": "Health Guidelines",
29
+ "17": "COVID-19 News",
30
+ "18": "Cybersecurity",
31
+ "19": "Hacking",
32
+ "20": "Malware",
33
+ "21": "Addiction",
34
+ "22": "Substance Abuse",
35
+ "23": "Rehabilitation",
36
+ "24": "Hate Speech",
37
+ "25": "Offensive Language",
38
+ "26": "Discrimination",
39
+ "27": "Racism",
40
+ "28": "Homophobia",
41
+ "29": "Accidents",
42
+ "30": "Disasters",
43
+ "31": "Public Safety",
44
+ "32": "Weapons",
45
+ "33": "Gun Control",
46
+ "34": "Firearms"
47
+ },
48
+ "initializer_range": 0.02,
49
+ "label2id": {
50
+ "Accidents": 29,
51
+ "Addiction": 21,
52
+ "Adult Content": 2,
53
+ "COVID-19 News": 17,
54
+ "Counterterrorism": 7,
55
+ "Crime": 3,
56
+ "Cybersecurity": 18,
57
+ "Disasters": 30,
58
+ "Discrimination": 26,
59
+ "Erotica": 1,
60
+ "Firearms": 34,
61
+ "Gun Control": 33,
62
+ "Hacking": 19,
63
+ "Hate Speech": 24,
64
+ "Health Guidelines": 16,
65
+ "Homophobia": 28,
66
+ "International Relations": 13,
67
+ "Malware": 20,
68
+ "Military Conflict": 11,
69
+ "Offensive Language": 25,
70
+ "Pandemic": 14,
71
+ "Pornography": 0,
72
+ "Public Safety": 31,
73
+ "Racism": 27,
74
+ "Rehabilitation": 23,
75
+ "Sexual Assault": 4,
76
+ "Smoking": 8,
77
+ "Substance Abuse": 22,
78
+ "Terrorist Attacks": 6,
79
+ "Tobacco Use": 10,
80
+ "Vaccines": 15,
81
+ "Vaping": 9,
82
+ "Violent Crime": 5,
83
+ "War": 12,
84
+ "Weapons": 32
85
+ },
86
+ "max_position_embeddings": 512,
87
+ "model_type": "distilbert",
88
+ "n_heads": 12,
89
+ "n_layers": 6,
90
+ "pad_token_id": 0,
91
+ "problem_type": "single_label_classification",
92
+ "qa_dropout": 0.1,
93
+ "seq_classif_dropout": 0.2,
94
+ "sinusoidal_pos_embds": false,
95
+ "tie_weights_": true,
96
+ "torch_dtype": "float32",
97
+ "transformers_version": "4.44.0",
98
+ "vocab_size": 30522
99
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba193e9692f59fa0b7f0574a00b09c5de3bfb20b956bb679449b7165478df348
3
+ size 267934084
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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": "DistilBertTokenizer",
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:e771fcb21953972cfcbf5157b06d4bb5cce3923942e4058bd66f7c1352339424
3
+ size 5240
vocab.txt ADDED
The diff for this file is too large to render. See raw diff