Sleoruiz commited on
Commit
4e70f3a
·
1 Parent(s): f61bff6

Training in progress, epoch 1

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 250101
3
+ }
config.json ADDED
@@ -0,0 +1,159 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/mdeberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "Administraci\u00f3n Central",
12
+ "1": "Aseguradora",
13
+ "2": "Asuntos de la mujer",
14
+ "3": "Banco de la Rep\u00fablica",
15
+ "4": "Bienes nacionales",
16
+ "5": "Calamidades p\u00fablicas",
17
+ "6": "Comercio Exterior",
18
+ "7": "Constituci\u00f3n",
19
+ "8": "Control de calidad",
20
+ "9": "Control fiscal",
21
+ "10": "Corporaciones Aut\u00f3nomas Regionales",
22
+ "11": "Cultura",
23
+ "12": "Defensa Nacional",
24
+ "13": "Diplomacia",
25
+ "14": "Ecolog\u00eda",
26
+ "15": "Educaci\u00f3n",
27
+ "16": "Empr\u00e9stitos",
28
+ "17": "Energ\u00eda",
29
+ "18": "Espacio A\u00e9reo",
30
+ "19": "Establecimientos p\u00fablico",
31
+ "20": "Fondos de prestaciones",
32
+ "21": "Fronteras",
33
+ "22": "Fuerza P\u00fablica",
34
+ "23": "Hacienda",
35
+ "24": "Impuestos",
36
+ "25": "Inform\u00e1tica",
37
+ "26": "Investigaci\u00f3n cient\u00edfica",
38
+ "27": "Legislaci\u00f3n administrativa",
39
+ "28": "Leyes",
40
+ "29": "Medio ambiente",
41
+ "30": "Medios de comunicaci\u00f3n",
42
+ "31": "Mercado de Valores",
43
+ "32": "Miner\u00eda",
44
+ "33": "Monopolios",
45
+ "34": "Monumentos p\u00fablicos",
46
+ "35": "Nacionalidad",
47
+ "36": "Organismos de Control",
48
+ "37": "Organizaciones sindicales",
49
+ "38": "Organizaci\u00f3n Territorial",
50
+ "39": "Planeaci\u00f3n nacional",
51
+ "40": "Pol\u00edtica Internacional",
52
+ "41": "Pol\u00edtica portuaria",
53
+ "42": "Pol\u00edticas migratorias",
54
+ "43": "Prestaciones Servidores P\u00fablicos",
55
+ "44": "Presupuesto",
56
+ "45": "Propiedad intelectual",
57
+ "46": "Recreaci\u00f3n",
58
+ "47": "Recursos ictiol\u00f3gicos",
59
+ "48": "Regulaci\u00f3n econ\u00f3mica",
60
+ "49": "Reubicaci\u00f3n de entidades",
61
+ "50": "R\u00e9gimen Agropecuario",
62
+ "51": "Salud",
63
+ "52": "Seguridad Social",
64
+ "53": "Servicios p\u00fablicos",
65
+ "54": "Sin clasificaci\u00f3n",
66
+ "55": "Tierras",
67
+ "56": "Transporte",
68
+ "57": "Turismo",
69
+ "58": "Vivienda",
70
+ "59": "Zona franca"
71
+ },
72
+ "initializer_range": 0.02,
73
+ "intermediate_size": 3072,
74
+ "label2id": {
75
+ "Administraci\u00f3n Central": 0,
76
+ "Aseguradora": 1,
77
+ "Asuntos de la mujer": 2,
78
+ "Banco de la Rep\u00fablica": 3,
79
+ "Bienes nacionales": 4,
80
+ "Calamidades p\u00fablicas": 5,
81
+ "Comercio Exterior": 6,
82
+ "Constituci\u00f3n": 7,
83
+ "Control de calidad": 8,
84
+ "Control fiscal": 9,
85
+ "Corporaciones Aut\u00f3nomas Regionales": 10,
86
+ "Cultura": 11,
87
+ "Defensa Nacional": 12,
88
+ "Diplomacia": 13,
89
+ "Ecolog\u00eda": 14,
90
+ "Educaci\u00f3n": 15,
91
+ "Empr\u00e9stitos": 16,
92
+ "Energ\u00eda": 17,
93
+ "Espacio A\u00e9reo": 18,
94
+ "Establecimientos p\u00fablico": 19,
95
+ "Fondos de prestaciones": 20,
96
+ "Fronteras": 21,
97
+ "Fuerza P\u00fablica": 22,
98
+ "Hacienda": 23,
99
+ "Impuestos": 24,
100
+ "Inform\u00e1tica": 25,
101
+ "Investigaci\u00f3n cient\u00edfica": 26,
102
+ "Legislaci\u00f3n administrativa": 27,
103
+ "Leyes": 28,
104
+ "Medio ambiente": 29,
105
+ "Medios de comunicaci\u00f3n": 30,
106
+ "Mercado de Valores": 31,
107
+ "Miner\u00eda": 32,
108
+ "Monopolios": 33,
109
+ "Monumentos p\u00fablicos": 34,
110
+ "Nacionalidad": 35,
111
+ "Organismos de Control": 36,
112
+ "Organizaciones sindicales": 37,
113
+ "Organizaci\u00f3n Territorial": 38,
114
+ "Planeaci\u00f3n nacional": 39,
115
+ "Pol\u00edtica Internacional": 40,
116
+ "Pol\u00edtica portuaria": 41,
117
+ "Pol\u00edticas migratorias": 42,
118
+ "Prestaciones Servidores P\u00fablicos": 43,
119
+ "Presupuesto": 44,
120
+ "Propiedad intelectual": 45,
121
+ "Recreaci\u00f3n": 46,
122
+ "Recursos ictiol\u00f3gicos": 47,
123
+ "Regulaci\u00f3n econ\u00f3mica": 48,
124
+ "Reubicaci\u00f3n de entidades": 49,
125
+ "R\u00e9gimen Agropecuario": 50,
126
+ "Salud": 51,
127
+ "Seguridad Social": 52,
128
+ "Servicios p\u00fablicos": 53,
129
+ "Sin clasificaci\u00f3n": 54,
130
+ "Tierras": 55,
131
+ "Transporte": 56,
132
+ "Turismo": 57,
133
+ "Vivienda": 58,
134
+ "Zona franca": 59
135
+ },
136
+ "layer_norm_eps": 1e-07,
137
+ "max_position_embeddings": 512,
138
+ "max_relative_positions": -1,
139
+ "model_type": "deberta-v2",
140
+ "norm_rel_ebd": "layer_norm",
141
+ "num_attention_heads": 12,
142
+ "num_hidden_layers": 12,
143
+ "pad_token_id": 0,
144
+ "pooler_dropout": 0,
145
+ "pooler_hidden_act": "gelu",
146
+ "pooler_hidden_size": 768,
147
+ "pos_att_type": [
148
+ "p2c",
149
+ "c2p"
150
+ ],
151
+ "position_biased_input": false,
152
+ "position_buckets": 256,
153
+ "relative_attention": true,
154
+ "share_att_key": true,
155
+ "torch_dtype": "float32",
156
+ "transformers_version": "4.28.1",
157
+ "type_vocab_size": 0,
158
+ "vocab_size": 251000
159
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66a438f9598a6b9b208f9556ed0d46c6cb634f3325a8e9cd60e0de59e0885c8b
3
+ size 1115494123
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
3
+ size 4305025
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b7176ac32cc1a8fdd65c26bbd7786cbb0308af2592ab5cebd333fdda4b63dd6
3
+ size 16331566
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": false,
6
+ "eos_token": "[SEP]",
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "split_by_punct": false,
13
+ "tokenizer_class": "DebertaV2Tokenizer",
14
+ "unk_token": "[UNK]",
15
+ "vocab_type": "spm"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:503b58a50fcd1392eea5a61fea48a3c02eb52e1d932d670b6672c31dca1a6f4b
3
+ size 3567