Training in progress, epoch 1
Browse files- config.json +153 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +65 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "PlanTL-GOB-ES/roberta-base-bne",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.15,
|
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": 0.15,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "Administraci\u00f3n Central",
|
16 |
+
"1": "Asuntos de la mujer",
|
17 |
+
"2": "Banco de la Rep\u00fablica",
|
18 |
+
"3": "Bienes nacionales",
|
19 |
+
"4": "Bonos del Estado",
|
20 |
+
"5": "Calamidades p\u00fablicas",
|
21 |
+
"6": "Comercio Exterior",
|
22 |
+
"7": "Constituci\u00f3n",
|
23 |
+
"8": "Control de calidad",
|
24 |
+
"9": "Control fiscal",
|
25 |
+
"10": "Corporaciones Aut\u00f3nomas Regionales",
|
26 |
+
"11": "Cultura",
|
27 |
+
"12": "Defensa Nacional",
|
28 |
+
"13": "Diplomacia",
|
29 |
+
"14": "Ecolog\u00eda",
|
30 |
+
"15": "Educaci\u00f3n",
|
31 |
+
"16": "Energ\u00eda",
|
32 |
+
"17": "Entidades Financieras",
|
33 |
+
"18": "Espacio A\u00e9reo",
|
34 |
+
"19": "Establecimientos p\u00fablico",
|
35 |
+
"20": "Fondos de prestaciones",
|
36 |
+
"21": "Fronteras",
|
37 |
+
"22": "Fuerza P\u00fablica",
|
38 |
+
"23": "Hacienda",
|
39 |
+
"24": "Impuestos",
|
40 |
+
"25": "Inform\u00e1tica",
|
41 |
+
"26": "Investigaci\u00f3n cient\u00edfica",
|
42 |
+
"27": "Legislaci\u00f3n administrativa",
|
43 |
+
"28": "Leyes",
|
44 |
+
"29": "Medio ambiente",
|
45 |
+
"30": "Medios de comunicaci\u00f3n",
|
46 |
+
"31": "Mercado de Valores",
|
47 |
+
"32": "Miner\u00eda",
|
48 |
+
"33": "Monopolios",
|
49 |
+
"34": "Monumentos p\u00fablicos",
|
50 |
+
"35": "Nacionalidad",
|
51 |
+
"36": "Organismos de Control",
|
52 |
+
"37": "Organizaciones sindicales",
|
53 |
+
"38": "Organizaci\u00f3n Territorial",
|
54 |
+
"39": "Planeaci\u00f3n nacional",
|
55 |
+
"40": "Pol\u00edtica Internacional",
|
56 |
+
"41": "Pol\u00edtica portuaria",
|
57 |
+
"42": "Pol\u00edticas migratorias",
|
58 |
+
"43": "Prestaciones Servidores P\u00fablicos",
|
59 |
+
"44": "Presupuesto",
|
60 |
+
"45": "Propiedad intelectual",
|
61 |
+
"46": "Recreaci\u00f3n",
|
62 |
+
"47": "Recursos ictiol\u00f3gicos",
|
63 |
+
"48": "Regulaci\u00f3n econ\u00f3mica",
|
64 |
+
"49": "Reubicaci\u00f3n de entidades",
|
65 |
+
"50": "R\u00e9gimen Agropecuario",
|
66 |
+
"51": "Salud",
|
67 |
+
"52": "Seguridad Social",
|
68 |
+
"53": "Servicios p\u00fablicos",
|
69 |
+
"54": "Sin clasificaci\u00f3n",
|
70 |
+
"55": "Tierras",
|
71 |
+
"56": "Transporte",
|
72 |
+
"57": "Turismo",
|
73 |
+
"58": "Vivienda",
|
74 |
+
"59": "Zona franca"
|
75 |
+
},
|
76 |
+
"initializer_range": 0.02,
|
77 |
+
"intermediate_size": 3072,
|
78 |
+
"label2id": {
|
79 |
+
"Administraci\u00f3n Central": 0,
|
80 |
+
"Asuntos de la mujer": 1,
|
81 |
+
"Banco de la Rep\u00fablica": 2,
|
82 |
+
"Bienes nacionales": 3,
|
83 |
+
"Bonos del Estado": 4,
|
84 |
+
"Calamidades p\u00fablicas": 5,
|
85 |
+
"Comercio Exterior": 6,
|
86 |
+
"Constituci\u00f3n": 7,
|
87 |
+
"Control de calidad": 8,
|
88 |
+
"Control fiscal": 9,
|
89 |
+
"Corporaciones Aut\u00f3nomas Regionales": 10,
|
90 |
+
"Cultura": 11,
|
91 |
+
"Defensa Nacional": 12,
|
92 |
+
"Diplomacia": 13,
|
93 |
+
"Ecolog\u00eda": 14,
|
94 |
+
"Educaci\u00f3n": 15,
|
95 |
+
"Energ\u00eda": 16,
|
96 |
+
"Entidades Financieras": 17,
|
97 |
+
"Espacio A\u00e9reo": 18,
|
98 |
+
"Establecimientos p\u00fablico": 19,
|
99 |
+
"Fondos de prestaciones": 20,
|
100 |
+
"Fronteras": 21,
|
101 |
+
"Fuerza P\u00fablica": 22,
|
102 |
+
"Hacienda": 23,
|
103 |
+
"Impuestos": 24,
|
104 |
+
"Inform\u00e1tica": 25,
|
105 |
+
"Investigaci\u00f3n cient\u00edfica": 26,
|
106 |
+
"Legislaci\u00f3n administrativa": 27,
|
107 |
+
"Leyes": 28,
|
108 |
+
"Medio ambiente": 29,
|
109 |
+
"Medios de comunicaci\u00f3n": 30,
|
110 |
+
"Mercado de Valores": 31,
|
111 |
+
"Miner\u00eda": 32,
|
112 |
+
"Monopolios": 33,
|
113 |
+
"Monumentos p\u00fablicos": 34,
|
114 |
+
"Nacionalidad": 35,
|
115 |
+
"Organismos de Control": 36,
|
116 |
+
"Organizaciones sindicales": 37,
|
117 |
+
"Organizaci\u00f3n Territorial": 38,
|
118 |
+
"Planeaci\u00f3n nacional": 39,
|
119 |
+
"Pol\u00edtica Internacional": 40,
|
120 |
+
"Pol\u00edtica portuaria": 41,
|
121 |
+
"Pol\u00edticas migratorias": 42,
|
122 |
+
"Prestaciones Servidores P\u00fablicos": 43,
|
123 |
+
"Presupuesto": 44,
|
124 |
+
"Propiedad intelectual": 45,
|
125 |
+
"Recreaci\u00f3n": 46,
|
126 |
+
"Recursos ictiol\u00f3gicos": 47,
|
127 |
+
"Regulaci\u00f3n econ\u00f3mica": 48,
|
128 |
+
"Reubicaci\u00f3n de entidades": 49,
|
129 |
+
"R\u00e9gimen Agropecuario": 50,
|
130 |
+
"Salud": 51,
|
131 |
+
"Seguridad Social": 52,
|
132 |
+
"Servicios p\u00fablicos": 53,
|
133 |
+
"Sin clasificaci\u00f3n": 54,
|
134 |
+
"Tierras": 55,
|
135 |
+
"Transporte": 56,
|
136 |
+
"Turismo": 57,
|
137 |
+
"Vivienda": 58,
|
138 |
+
"Zona franca": 59
|
139 |
+
},
|
140 |
+
"layer_norm_eps": 1e-05,
|
141 |
+
"max_position_embeddings": 514,
|
142 |
+
"model_type": "roberta",
|
143 |
+
"num_attention_heads": 12,
|
144 |
+
"num_hidden_layers": 12,
|
145 |
+
"pad_token_id": 1,
|
146 |
+
"position_embedding_type": "absolute",
|
147 |
+
"problem_type": "single_label_classification",
|
148 |
+
"torch_dtype": "float32",
|
149 |
+
"transformers_version": "4.33.1",
|
150 |
+
"type_vocab_size": 1,
|
151 |
+
"use_cache": true,
|
152 |
+
"vocab_size": 50262
|
153 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20e988803394d3816c2b3b02b5458e16030fb2a8a922b70999a66c9d8bced33b
|
3 |
+
size 498826801
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
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 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"clean_up_tokenization_spaces": true,
|
12 |
+
"cls_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"eos_token": {
|
21 |
+
"__type": "AddedToken",
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"errors": "replace",
|
29 |
+
"mask_token": {
|
30 |
+
"__type": "AddedToken",
|
31 |
+
"content": "<mask>",
|
32 |
+
"lstrip": true,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"max_len": 512,
|
38 |
+
"model_max_length": 512,
|
39 |
+
"pad_token": {
|
40 |
+
"__type": "AddedToken",
|
41 |
+
"content": "<pad>",
|
42 |
+
"lstrip": false,
|
43 |
+
"normalized": true,
|
44 |
+
"rstrip": false,
|
45 |
+
"single_word": false
|
46 |
+
},
|
47 |
+
"sep_token": {
|
48 |
+
"__type": "AddedToken",
|
49 |
+
"content": "</s>",
|
50 |
+
"lstrip": false,
|
51 |
+
"normalized": true,
|
52 |
+
"rstrip": false,
|
53 |
+
"single_word": false
|
54 |
+
},
|
55 |
+
"tokenizer_class": "RobertaTokenizer",
|
56 |
+
"trim_offsets": true,
|
57 |
+
"unk_token": {
|
58 |
+
"__type": "AddedToken",
|
59 |
+
"content": "<unk>",
|
60 |
+
"lstrip": false,
|
61 |
+
"normalized": true,
|
62 |
+
"rstrip": false,
|
63 |
+
"single_word": false
|
64 |
+
}
|
65 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6cfaec8e23bb776be6c291e28cd8a29b65c61a3ade19f10cb55856f2590be2a
|
3 |
+
size 4027
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|