taro-pudding commited on
Commit
88ef70f
1 Parent(s): b594bad

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,39 +1,143 @@
1
  {
2
- "_name_or_path": "gpt2",
3
- "activation_function": "gelu_new",
4
  "architectures": [
5
- "GPT2LMHeadModel"
6
  ],
7
- "attn_pdrop": 0.1,
8
- "bos_token_id": 50256,
9
- "embd_pdrop": 0.1,
10
- "eos_token_id": 50256,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  "initializer_range": 0.02,
12
- "layer_norm_epsilon": 1e-05,
13
- "model_type": "gpt2",
14
- "n_ctx": 1024,
15
- "n_embd": 768,
16
- "n_head": 12,
17
- "n_inner": null,
18
- "n_layer": 12,
19
- "n_positions": 1024,
20
- "reorder_and_upcast_attn": false,
21
- "resid_pdrop": 0.1,
22
- "scale_attn_by_inverse_layer_idx": false,
23
- "scale_attn_weights": true,
24
- "summary_activation": null,
25
- "summary_first_dropout": 0.1,
26
- "summary_proj_to_labels": true,
27
- "summary_type": "cls_index",
28
- "summary_use_proj": true,
29
- "task_specific_params": {
30
- "text-generation": {
31
- "do_sample": true,
32
- "max_length": 50
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34
  },
 
 
 
 
 
 
 
 
 
 
35
  "torch_dtype": "float32",
36
  "transformers_version": "4.40.0",
37
- "use_cache": true,
38
- "vocab_size": 50257
39
  }
 
1
  {
2
+ "_name_or_path": "distilbert-base-multilingual-cased",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForTokenClassification"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-USERNAME",
14
+ "2": "I-USERNAME",
15
+ "3": "B-TIME",
16
+ "4": "I-TIME",
17
+ "5": "B-DATE",
18
+ "6": "I-DATE",
19
+ "7": "B-LASTNAME1",
20
+ "8": "I-LASTNAME1",
21
+ "9": "B-LASTNAME2",
22
+ "10": "I-LASTNAME2",
23
+ "11": "B-EMAIL",
24
+ "12": "I-EMAIL",
25
+ "13": "B-SOCIALNUMBER",
26
+ "14": "I-SOCIALNUMBER",
27
+ "15": "B-IDCARD",
28
+ "16": "I-IDCARD",
29
+ "17": "B-COUNTRY",
30
+ "18": "B-BUILDING",
31
+ "19": "B-STREET",
32
+ "20": "I-STREET",
33
+ "21": "B-CITY",
34
+ "22": "B-STATE",
35
+ "23": "I-STATE",
36
+ "24": "B-POSTCODE",
37
+ "25": "I-POSTCODE",
38
+ "26": "B-PASS",
39
+ "27": "I-PASS",
40
+ "28": "I-COUNTRY",
41
+ "29": "I-CITY",
42
+ "30": "B-PASSPORT",
43
+ "31": "I-PASSPORT",
44
+ "32": "B-TEL",
45
+ "33": "I-TEL",
46
+ "34": "B-DRIVERLICENSE",
47
+ "35": "I-DRIVERLICENSE",
48
+ "36": "B-BOD",
49
+ "37": "I-BOD",
50
+ "38": "B-SEX",
51
+ "39": "B-IP",
52
+ "40": "I-IP",
53
+ "41": "I-SEX",
54
+ "42": "I-BUILDING",
55
+ "43": "B-SECADDRESS",
56
+ "44": "I-SECADDRESS",
57
+ "45": "B-LASTNAME3",
58
+ "46": "I-LASTNAME3",
59
+ "47": "B-GIVENNAME1",
60
+ "48": "I-GIVENNAME1",
61
+ "49": "B-GIVENNAME2",
62
+ "50": "I-GIVENNAME2",
63
+ "51": "B-TITLE",
64
+ "52": "I-TITLE",
65
+ "53": "B-GEOCOORD",
66
+ "54": "I-GEOCOORD",
67
+ "55": "B-CARDISSUER",
68
+ "56": "I-CARDISSUER"
69
+ },
70
  "initializer_range": 0.02,
71
+ "label2id": {
72
+ "B-BOD": 36,
73
+ "B-BUILDING": 18,
74
+ "B-CARDISSUER": 55,
75
+ "B-CITY": 21,
76
+ "B-COUNTRY": 17,
77
+ "B-DATE": 5,
78
+ "B-DRIVERLICENSE": 34,
79
+ "B-EMAIL": 11,
80
+ "B-GEOCOORD": 53,
81
+ "B-GIVENNAME1": 47,
82
+ "B-GIVENNAME2": 49,
83
+ "B-IDCARD": 15,
84
+ "B-IP": 39,
85
+ "B-LASTNAME1": 7,
86
+ "B-LASTNAME2": 9,
87
+ "B-LASTNAME3": 45,
88
+ "B-PASS": 26,
89
+ "B-PASSPORT": 30,
90
+ "B-POSTCODE": 24,
91
+ "B-SECADDRESS": 43,
92
+ "B-SEX": 38,
93
+ "B-SOCIALNUMBER": 13,
94
+ "B-STATE": 22,
95
+ "B-STREET": 19,
96
+ "B-TEL": 32,
97
+ "B-TIME": 3,
98
+ "B-TITLE": 51,
99
+ "B-USERNAME": 1,
100
+ "I-BOD": 37,
101
+ "I-BUILDING": 42,
102
+ "I-CARDISSUER": 56,
103
+ "I-CITY": 29,
104
+ "I-COUNTRY": 28,
105
+ "I-DATE": 6,
106
+ "I-DRIVERLICENSE": 35,
107
+ "I-EMAIL": 12,
108
+ "I-GEOCOORD": 54,
109
+ "I-GIVENNAME1": 48,
110
+ "I-GIVENNAME2": 50,
111
+ "I-IDCARD": 16,
112
+ "I-IP": 40,
113
+ "I-LASTNAME1": 8,
114
+ "I-LASTNAME2": 10,
115
+ "I-LASTNAME3": 46,
116
+ "I-PASS": 27,
117
+ "I-PASSPORT": 31,
118
+ "I-POSTCODE": 25,
119
+ "I-SECADDRESS": 44,
120
+ "I-SEX": 41,
121
+ "I-SOCIALNUMBER": 14,
122
+ "I-STATE": 23,
123
+ "I-STREET": 20,
124
+ "I-TEL": 33,
125
+ "I-TIME": 4,
126
+ "I-TITLE": 52,
127
+ "I-USERNAME": 2,
128
+ "O": 0
129
  },
130
+ "max_position_embeddings": 512,
131
+ "model_type": "distilbert",
132
+ "n_heads": 12,
133
+ "n_layers": 6,
134
+ "output_past": true,
135
+ "pad_token_id": 0,
136
+ "qa_dropout": 0.1,
137
+ "seq_classif_dropout": 0.2,
138
+ "sinusoidal_pos_embds": false,
139
+ "tie_weights_": true,
140
  "torch_dtype": "float32",
141
  "transformers_version": "4.40.0",
142
+ "vocab_size": 119547
 
143
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2298f3fe4057e27eef1e1690194058e11214047881e9a020c1cefeaf7538ae16
3
- size 497774208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a1910b4bd87a29720075e239751a41abfffe21b8a31b10ad024dd98aeab5440
3
+ size 539124012
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": false,
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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5c986f018b30c647335012dcc40d78616916772b89e43d5144d64378eb2e44d
3
- size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb737042e3860614bdd6ae821be207f21e3a713877948632955c0434e443bd8
3
+ size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff