wgj0714 commited on
Commit
3014b68
1 Parent(s): 8109a6a

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/roberta-large",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "a_criminal record",
16
+ "1": "a_job",
17
+ "2": "a_name",
18
+ "3": "a_v_relation",
19
+ "4": "acq_adress",
20
+ "5": "acq_asset_amount",
21
+ "6": "acq_datetime",
22
+ "7": "acq_method",
23
+ "8": "acq_name",
24
+ "9": "approach_method",
25
+ "10": "attempt_reason",
26
+ "11": "content_detail",
27
+ "12": "content_item",
28
+ "13": "content_method",
29
+ "14": "content_payment_made",
30
+ "15": "content_payment_method",
31
+ "16": "content_purchase_int",
32
+ "17": "content_quality",
33
+ "18": "content_space",
34
+ "19": "crime_address",
35
+ "20": "crime_datetime",
36
+ "21": "crime_result_attempted",
37
+ "22": "crime_result_completed",
38
+ "23": "criminal_intent",
39
+ "24": "d_address",
40
+ "25": "d_asset_amount",
41
+ "26": "d_datetime",
42
+ "27": "d_method",
43
+ "28": "degree_intent_to_pay",
44
+ "29": "degree_item",
45
+ "30": "degree_purchase_ability",
46
+ "31": "degree_quality",
47
+ "32": "degree_quantity",
48
+ "33": "means_etc",
49
+ "34": "means_person",
50
+ "35": "means_verbal",
51
+ "36": "total_amount",
52
+ "37": "v_age",
53
+ "38": "v_decieve_reason",
54
+ "39": "v_job",
55
+ "40": "v_med_rec",
56
+ "41": "v_name",
57
+ "42": "v_sex"
58
+ },
59
+ "initializer_range": 0.02,
60
+ "intermediate_size": 4096,
61
+ "label2id": {
62
+ "a_criminal record": 0,
63
+ "a_job": 1,
64
+ "a_name": 2,
65
+ "a_v_relation": 3,
66
+ "acq_adress": 4,
67
+ "acq_asset_amount": 5,
68
+ "acq_datetime": 6,
69
+ "acq_method": 7,
70
+ "acq_name": 8,
71
+ "approach_method": 9,
72
+ "attempt_reason": 10,
73
+ "content_detail": 11,
74
+ "content_item": 12,
75
+ "content_method": 13,
76
+ "content_payment_made": 14,
77
+ "content_payment_method": 15,
78
+ "content_purchase_int": 16,
79
+ "content_quality": 17,
80
+ "content_space": 18,
81
+ "crime_address": 19,
82
+ "crime_datetime": 20,
83
+ "crime_result_attempted": 21,
84
+ "crime_result_completed": 22,
85
+ "criminal_intent": 23,
86
+ "d_address": 24,
87
+ "d_asset_amount": 25,
88
+ "d_datetime": 26,
89
+ "d_method": 27,
90
+ "degree_intent_to_pay": 28,
91
+ "degree_item": 29,
92
+ "degree_purchase_ability": 30,
93
+ "degree_quality": 31,
94
+ "degree_quantity": 32,
95
+ "means_etc": 33,
96
+ "means_person": 34,
97
+ "means_verbal": 35,
98
+ "total_amount": 36,
99
+ "v_age": 37,
100
+ "v_decieve_reason": 38,
101
+ "v_job": 39,
102
+ "v_med_rec": 40,
103
+ "v_name": 41,
104
+ "v_sex": 42
105
+ },
106
+ "layer_norm_eps": 1e-05,
107
+ "max_position_embeddings": 514,
108
+ "model_type": "roberta",
109
+ "num_attention_heads": 16,
110
+ "num_hidden_layers": 24,
111
+ "pad_token_id": 1,
112
+ "position_embedding_type": "absolute",
113
+ "problem_type": "single_label_classification",
114
+ "tokenizer_class": "BertTokenizer",
115
+ "torch_dtype": "float32",
116
+ "transformers_version": "4.39.3",
117
+ "type_vocab_size": 1,
118
+ "use_cache": true,
119
+ "vocab_size": 32000
120
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95030dd9646520ea384caf2e7cd23fbdc3c7b3f1ce704be0a4cca7b7827fa5bd
3
+ size 1346850020
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[CLS]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
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
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": false,
49
+ "eos_token": "[SEP]",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66378bbe2d32c26779eaad3607856b2bc54f965602abb57a50c9baa090b8ae06
3
+ size 4920
vocab.txt ADDED
The diff for this file is too large to render. See raw diff