Training in progress, epoch 1
Browse files- .gitignore +1 -0
- 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
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "PlanTL-GOB-ES/RoBERTalex",
|
| 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": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "Sin clasificaci\u00f3n",
|
| 16 |
+
"1": "Administraci\u00f3n Central",
|
| 17 |
+
"2": "Organismos de Control",
|
| 18 |
+
"3": "Organizaci\u00f3n Territorial",
|
| 19 |
+
"4": "Reubicaci\u00f3n de entidades",
|
| 20 |
+
"5": "Leyes",
|
| 21 |
+
"6": "Constituci\u00f3n",
|
| 22 |
+
"7": "Pol\u00edtica Internacional",
|
| 23 |
+
"8": "Defensa Nacional",
|
| 24 |
+
"9": "Fuerza P\u00fablica",
|
| 25 |
+
"10": "Diplomacia",
|
| 26 |
+
"11": "Comercio Exterior",
|
| 27 |
+
"12": "Pol\u00edtica portuaria",
|
| 28 |
+
"13": "Fronteras",
|
| 29 |
+
"14": "Nacionalidad",
|
| 30 |
+
"15": "Monumentos p\u00fablicos",
|
| 31 |
+
"16": "Pol\u00edticas migratorias",
|
| 32 |
+
"17": "Zona franca",
|
| 33 |
+
"18": "Hacienda",
|
| 34 |
+
"19": "Impuestos",
|
| 35 |
+
"20": "Regulaci\u00f3n econ\u00f3mica",
|
| 36 |
+
"21": "Banco de la Rep\u00fablica",
|
| 37 |
+
"22": "Monopolios",
|
| 38 |
+
"23": "Empr\u00e9stitos",
|
| 39 |
+
"24": "Mercado de Valores",
|
| 40 |
+
"25": "Planeaci\u00f3n nacional",
|
| 41 |
+
"26": "Aseguradora",
|
| 42 |
+
"27": "Presupuesto",
|
| 43 |
+
"28": "Control fiscal",
|
| 44 |
+
"29": "Bienes nacionales",
|
| 45 |
+
"30": "Propiedad intelectual",
|
| 46 |
+
"31": "Establecimientos p\u00fablico",
|
| 47 |
+
"32": "Control de calidad",
|
| 48 |
+
"33": "Legislaci\u00f3n administrativa",
|
| 49 |
+
"34": "R\u00e9gimen Agropecuario",
|
| 50 |
+
"35": "Ecolog\u00eda",
|
| 51 |
+
"36": "Medio ambiente",
|
| 52 |
+
"37": "Tierras",
|
| 53 |
+
"38": "Recursos ictiol\u00f3gicos",
|
| 54 |
+
"39": "Miner\u00eda",
|
| 55 |
+
"40": "Energ\u00eda",
|
| 56 |
+
"41": "Corporaciones Aut\u00f3nomas Regionales",
|
| 57 |
+
"42": "Medios de comunicaci\u00f3n",
|
| 58 |
+
"43": "Calamidades p\u00fablicas",
|
| 59 |
+
"44": "Servicios p\u00fablicos",
|
| 60 |
+
"45": "Investigaci\u00f3n cient\u00edfica",
|
| 61 |
+
"46": "Inform\u00e1tica",
|
| 62 |
+
"47": "Espacio A\u00e9reo",
|
| 63 |
+
"48": "Transporte",
|
| 64 |
+
"49": "Turismo",
|
| 65 |
+
"50": "Educaci\u00f3n",
|
| 66 |
+
"51": "Cultura",
|
| 67 |
+
"52": "Organizaciones sindicales",
|
| 68 |
+
"53": "Prestaciones Servidores P\u00fablicos",
|
| 69 |
+
"54": "Seguridad Social",
|
| 70 |
+
"55": "Fondos de prestaciones",
|
| 71 |
+
"56": "Recreaci\u00f3n",
|
| 72 |
+
"57": "Salud",
|
| 73 |
+
"58": "Vivienda",
|
| 74 |
+
"59": "Asuntos de la mujer"
|
| 75 |
+
},
|
| 76 |
+
"initializer_range": 0.02,
|
| 77 |
+
"intermediate_size": 3072,
|
| 78 |
+
"label2id": {
|
| 79 |
+
"Administraci\u00f3n Central": 1,
|
| 80 |
+
"Aseguradora": 26,
|
| 81 |
+
"Asuntos de la mujer": 59,
|
| 82 |
+
"Banco de la Rep\u00fablica": 21,
|
| 83 |
+
"Bienes nacionales": 29,
|
| 84 |
+
"Calamidades p\u00fablicas": 43,
|
| 85 |
+
"Comercio Exterior": 11,
|
| 86 |
+
"Constituci\u00f3n": 6,
|
| 87 |
+
"Control de calidad": 32,
|
| 88 |
+
"Control fiscal": 28,
|
| 89 |
+
"Corporaciones Aut\u00f3nomas Regionales": 41,
|
| 90 |
+
"Cultura": 51,
|
| 91 |
+
"Defensa Nacional": 8,
|
| 92 |
+
"Diplomacia": 10,
|
| 93 |
+
"Ecolog\u00eda": 35,
|
| 94 |
+
"Educaci\u00f3n": 50,
|
| 95 |
+
"Empr\u00e9stitos": 23,
|
| 96 |
+
"Energ\u00eda": 40,
|
| 97 |
+
"Espacio A\u00e9reo": 47,
|
| 98 |
+
"Establecimientos p\u00fablico": 31,
|
| 99 |
+
"Fondos de prestaciones": 55,
|
| 100 |
+
"Fronteras": 13,
|
| 101 |
+
"Fuerza P\u00fablica": 9,
|
| 102 |
+
"Hacienda": 18,
|
| 103 |
+
"Impuestos": 19,
|
| 104 |
+
"Inform\u00e1tica": 46,
|
| 105 |
+
"Investigaci\u00f3n cient\u00edfica": 45,
|
| 106 |
+
"Legislaci\u00f3n administrativa": 33,
|
| 107 |
+
"Leyes": 5,
|
| 108 |
+
"Medio ambiente": 36,
|
| 109 |
+
"Medios de comunicaci\u00f3n": 42,
|
| 110 |
+
"Mercado de Valores": 24,
|
| 111 |
+
"Miner\u00eda": 39,
|
| 112 |
+
"Monopolios": 22,
|
| 113 |
+
"Monumentos p\u00fablicos": 15,
|
| 114 |
+
"Nacionalidad": 14,
|
| 115 |
+
"Organismos de Control": 2,
|
| 116 |
+
"Organizaciones sindicales": 52,
|
| 117 |
+
"Organizaci\u00f3n Territorial": 3,
|
| 118 |
+
"Planeaci\u00f3n nacional": 25,
|
| 119 |
+
"Pol\u00edtica Internacional": 7,
|
| 120 |
+
"Pol\u00edtica portuaria": 12,
|
| 121 |
+
"Pol\u00edticas migratorias": 16,
|
| 122 |
+
"Prestaciones Servidores P\u00fablicos": 53,
|
| 123 |
+
"Presupuesto": 27,
|
| 124 |
+
"Propiedad intelectual": 30,
|
| 125 |
+
"Recreaci\u00f3n": 56,
|
| 126 |
+
"Recursos ictiol\u00f3gicos": 38,
|
| 127 |
+
"Regulaci\u00f3n econ\u00f3mica": 20,
|
| 128 |
+
"Reubicaci\u00f3n de entidades": 4,
|
| 129 |
+
"R\u00e9gimen Agropecuario": 34,
|
| 130 |
+
"Salud": 57,
|
| 131 |
+
"Seguridad Social": 54,
|
| 132 |
+
"Servicios p\u00fablicos": 44,
|
| 133 |
+
"Sin clasificaci\u00f3n": 0,
|
| 134 |
+
"Tierras": 37,
|
| 135 |
+
"Transporte": 48,
|
| 136 |
+
"Turismo": 49,
|
| 137 |
+
"Vivienda": 58,
|
| 138 |
+
"Zona franca": 17
|
| 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": "multi_label_classification",
|
| 148 |
+
"torch_dtype": "float32",
|
| 149 |
+
"transformers_version": "4.28.1",
|
| 150 |
+
"type_vocab_size": 1,
|
| 151 |
+
"use_cache": true,
|
| 152 |
+
"vocab_size": 52000
|
| 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 sha256:93bbd04ca3cdd4a0677aae33d1d203dbf9a56ec75d7955e06a6acde4e5bc7bde
|
| 3 |
+
size 504168621
|
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": true,
|
| 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:f1503d24a26b1220b2c103ebd9c290b50ecc897fb208f98ac422a024b3dc8bd3
|
| 3 |
+
size 3567
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|