Everither commited on
Commit
c93b517
·
verified ·
1 Parent(s): efc1520

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "Library",
14
+ "1": "Human-Trafficking",
15
+ "10": "Locked",
16
+ "11": "Porno",
17
+ "12": "Hacking",
18
+ "13": "Art",
19
+ "14": "Forum",
20
+ "15": "Marketplace",
21
+ "16": "Counterfeit Money",
22
+ "17": "Violence",
23
+ "18": "Fraud",
24
+ "19": "Casino",
25
+ "2": "Drugs",
26
+ "20": "Politics",
27
+ "21": "Services",
28
+ "22": "Social-Network",
29
+ "23": "Cryptolocker",
30
+ "24": "Cryptocurrency",
31
+ "25": "Counterfeit Credit-Cards",
32
+ "3": "Down",
33
+ "4": "Counterfeit Personal-Identification",
34
+ "5": "Religion",
35
+ "6": "Personal",
36
+ "7": "Leaked-Data",
37
+ "8": "Empty",
38
+ "9": "Hosting"
39
+ },
40
+ "initializer_range": 0.02,
41
+ "intermediate_size": 3072,
42
+ "label2id": {
43
+ "Art": 13,
44
+ "Casino": 19,
45
+ "Counterfeit Credit-Cards": 25,
46
+ "Counterfeit Money": 16,
47
+ "Counterfeit Personal-Identification": 4,
48
+ "Cryptocurrency": 24,
49
+ "Cryptolocker": 23,
50
+ "Down": 3,
51
+ "Drugs": 2,
52
+ "Empty": 8,
53
+ "Forum": 14,
54
+ "Fraud": 18,
55
+ "Hacking": 12,
56
+ "Hosting": 9,
57
+ "Human-Trafficking": 1,
58
+ "Leaked-Data": 7,
59
+ "Library": 0,
60
+ "Locked": 10,
61
+ "Marketplace": 15,
62
+ "Personal": 6,
63
+ "Politics": 20,
64
+ "Porno": 11,
65
+ "Religion": 5,
66
+ "Services": 21,
67
+ "Social-Network": 22,
68
+ "Violence": 17
69
+ },
70
+ "layer_norm_eps": 1e-12,
71
+ "max_position_embeddings": 512,
72
+ "model_type": "bert",
73
+ "num_attention_heads": 12,
74
+ "num_hidden_layers": 12,
75
+ "pad_token_id": 0,
76
+ "position_embedding_type": "absolute",
77
+ "problem_type": "single_label_classification",
78
+ "transformers_version": "4.57.1",
79
+ "type_vocab_size": 2,
80
+ "use_cache": true,
81
+ "vocab_size": 30522
82
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c49656a30392ed7594a29f1ef6afc012ccfc4932b9eabc73199fe04eabbc94d
3
+ size 438032472
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ff352450bfd64627200ac9048b94bf3677736b7732ddbb6a2aade72405de5fd
3
+ size 5841
vocab.txt ADDED
The diff for this file is too large to render. See raw diff