tiagoblima
commited on
Commit
•
f3e641c
1
Parent(s):
51cf046
Training in progress, step 1000
Browse files- config.json +125 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "neuralmind/bert-base-portuguese-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "cenarios-2017",
|
14 |
+
"1": "topofmind",
|
15 |
+
"2": "multimidia",
|
16 |
+
"3": "mercado",
|
17 |
+
"4": "tec",
|
18 |
+
"5": "ambiente",
|
19 |
+
"6": "opiniao",
|
20 |
+
"7": "o-melhor-de-sao-paulo",
|
21 |
+
"8": "especial",
|
22 |
+
"9": "ilustrada",
|
23 |
+
"10": "infograficos",
|
24 |
+
"11": "equilibrioesaude",
|
25 |
+
"12": "sobretudo",
|
26 |
+
"13": "serafina",
|
27 |
+
"14": "esporte",
|
28 |
+
"15": "guia-de-livros-discos-filmes",
|
29 |
+
"16": "seminariosfolha",
|
30 |
+
"17": "turismo",
|
31 |
+
"18": "rfi",
|
32 |
+
"19": "bichos",
|
33 |
+
"20": "saopaulo",
|
34 |
+
"21": "asmais",
|
35 |
+
"22": "folhinha",
|
36 |
+
"23": "mundo",
|
37 |
+
"24": "ombudsman",
|
38 |
+
"25": "vice",
|
39 |
+
"26": "treinamentocienciaesaude",
|
40 |
+
"27": "tv",
|
41 |
+
"28": "ciencia",
|
42 |
+
"29": "bbc",
|
43 |
+
"30": "ilustrissima",
|
44 |
+
"31": "comida",
|
45 |
+
"32": "dw",
|
46 |
+
"33": "treinamento",
|
47 |
+
"34": "empreendedorsocial",
|
48 |
+
"35": "mulher",
|
49 |
+
"36": "educacao",
|
50 |
+
"37": "guia-de-livros-filmes-discos",
|
51 |
+
"38": "poder",
|
52 |
+
"39": "paineldoleitor",
|
53 |
+
"40": "euronews",
|
54 |
+
"41": "colunas",
|
55 |
+
"42": "cotidiano",
|
56 |
+
"43": "banco-de-dados"
|
57 |
+
},
|
58 |
+
"initializer_range": 0.02,
|
59 |
+
"intermediate_size": 3072,
|
60 |
+
"label2id": {
|
61 |
+
"ambiente": 5,
|
62 |
+
"asmais": 21,
|
63 |
+
"banco-de-dados": 43,
|
64 |
+
"bbc": 29,
|
65 |
+
"bichos": 19,
|
66 |
+
"cenarios-2017": 0,
|
67 |
+
"ciencia": 28,
|
68 |
+
"colunas": 41,
|
69 |
+
"comida": 31,
|
70 |
+
"cotidiano": 42,
|
71 |
+
"dw": 32,
|
72 |
+
"educacao": 36,
|
73 |
+
"empreendedorsocial": 34,
|
74 |
+
"equilibrioesaude": 11,
|
75 |
+
"especial": 8,
|
76 |
+
"esporte": 14,
|
77 |
+
"euronews": 40,
|
78 |
+
"folhinha": 22,
|
79 |
+
"guia-de-livros-discos-filmes": 15,
|
80 |
+
"guia-de-livros-filmes-discos": 37,
|
81 |
+
"ilustrada": 9,
|
82 |
+
"ilustrissima": 30,
|
83 |
+
"infograficos": 10,
|
84 |
+
"mercado": 3,
|
85 |
+
"mulher": 35,
|
86 |
+
"multimidia": 2,
|
87 |
+
"mundo": 23,
|
88 |
+
"o-melhor-de-sao-paulo": 7,
|
89 |
+
"ombudsman": 24,
|
90 |
+
"opiniao": 6,
|
91 |
+
"paineldoleitor": 39,
|
92 |
+
"poder": 38,
|
93 |
+
"rfi": 18,
|
94 |
+
"saopaulo": 20,
|
95 |
+
"seminariosfolha": 16,
|
96 |
+
"serafina": 13,
|
97 |
+
"sobretudo": 12,
|
98 |
+
"tec": 4,
|
99 |
+
"topofmind": 1,
|
100 |
+
"treinamento": 33,
|
101 |
+
"treinamentocienciaesaude": 26,
|
102 |
+
"turismo": 17,
|
103 |
+
"tv": 27,
|
104 |
+
"vice": 25
|
105 |
+
},
|
106 |
+
"layer_norm_eps": 1e-12,
|
107 |
+
"max_position_embeddings": 512,
|
108 |
+
"model_type": "bert",
|
109 |
+
"num_attention_heads": 12,
|
110 |
+
"num_hidden_layers": 12,
|
111 |
+
"output_past": true,
|
112 |
+
"pad_token_id": 0,
|
113 |
+
"pooler_fc_size": 768,
|
114 |
+
"pooler_num_attention_heads": 12,
|
115 |
+
"pooler_num_fc_layers": 3,
|
116 |
+
"pooler_size_per_head": 128,
|
117 |
+
"pooler_type": "first_token_transform",
|
118 |
+
"position_embedding_type": "absolute",
|
119 |
+
"problem_type": "single_label_classification",
|
120 |
+
"torch_dtype": "float32",
|
121 |
+
"transformers_version": "4.41.2",
|
122 |
+
"type_vocab_size": 2,
|
123 |
+
"use_cache": true,
|
124 |
+
"vocab_size": 29794
|
125 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1f3dbbf2d4d2c08b98a4da4a0bd13a79607124d7552f9c26a037c825cd3563d
|
3 |
+
size 435851416
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2aeb847e5a1a13a0ac121656f8590f827c82f1fa236b0f757b5a04a977ccd1da
|
3 |
+
size 5112
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|