tiagoblima commited on
Commit
05de958
1 Parent(s): cbad243

Training in progress, step 5000

Browse files
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": "poder",
14
+ "1": "ilustrada",
15
+ "2": "mercado",
16
+ "3": "mundo",
17
+ "4": "esporte",
18
+ "5": "tec",
19
+ "6": "cotidiano",
20
+ "7": "ambiente",
21
+ "8": "equilibrioesaude",
22
+ "9": "sobretudo",
23
+ "10": "colunas",
24
+ "11": "educacao",
25
+ "12": "tv",
26
+ "13": "banco-de-dados",
27
+ "14": "opiniao",
28
+ "15": "ciencia",
29
+ "16": "paineldoleitor",
30
+ "17": "saopaulo",
31
+ "18": "ilustrissima",
32
+ "19": "seminariosfolha",
33
+ "20": "turismo",
34
+ "21": "empreendedorsocial",
35
+ "22": "serafina",
36
+ "23": "asmais",
37
+ "24": "o-melhor-de-sao-paulo",
38
+ "25": "bbc",
39
+ "26": "comida",
40
+ "27": "folhinha",
41
+ "28": "especial",
42
+ "29": "treinamento",
43
+ "30": "multimidia",
44
+ "31": "cenarios-2017",
45
+ "32": "topofmind",
46
+ "33": "dw",
47
+ "34": "ombudsman",
48
+ "35": "mulher",
49
+ "36": "guia-de-livros-discos-filmes",
50
+ "37": "treinamentocienciaesaude",
51
+ "38": "rfi",
52
+ "39": "vice",
53
+ "40": "bichos",
54
+ "41": "euronews",
55
+ "42": "guia-de-livros-filmes-discos",
56
+ "43": "infograficos"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "label2id": {
61
+ "ambiente": 7,
62
+ "asmais": 23,
63
+ "banco-de-dados": 13,
64
+ "bbc": 25,
65
+ "bichos": 40,
66
+ "cenarios-2017": 31,
67
+ "ciencia": 15,
68
+ "colunas": 10,
69
+ "comida": 26,
70
+ "cotidiano": 6,
71
+ "dw": 33,
72
+ "educacao": 11,
73
+ "empreendedorsocial": 21,
74
+ "equilibrioesaude": 8,
75
+ "especial": 28,
76
+ "esporte": 4,
77
+ "euronews": 41,
78
+ "folhinha": 27,
79
+ "guia-de-livros-discos-filmes": 36,
80
+ "guia-de-livros-filmes-discos": 42,
81
+ "ilustrada": 1,
82
+ "ilustrissima": 18,
83
+ "infograficos": 43,
84
+ "mercado": 2,
85
+ "mulher": 35,
86
+ "multimidia": 30,
87
+ "mundo": 3,
88
+ "o-melhor-de-sao-paulo": 24,
89
+ "ombudsman": 34,
90
+ "opiniao": 14,
91
+ "paineldoleitor": 16,
92
+ "poder": 0,
93
+ "rfi": 38,
94
+ "saopaulo": 17,
95
+ "seminariosfolha": 19,
96
+ "serafina": 22,
97
+ "sobretudo": 9,
98
+ "tec": 5,
99
+ "topofmind": 32,
100
+ "treinamento": 29,
101
+ "treinamentocienciaesaude": 37,
102
+ "turismo": 20,
103
+ "tv": 12,
104
+ "vice": 39
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 sha256:1b70146102124c241935b8b1a918b8aeb0ec3037d6f11e4aa886133b6e23f4c8
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 sha256:38f4b0c55b5e509cce9de357522fd29e149d9d20d6bc3c06e79a393452898c49
3
+ size 5112
vocab.txt ADDED
The diff for this file is too large to render. See raw diff