dougtrajano commited on
Commit
d40f285
1 Parent(s): 1d7a54e

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "neuralmind/bert-base-portuguese-cased",
3
+ "architectures": [
4
+ "ToxicityTypeForSequenceClassification"
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": "health",
14
+ "1": "ideology",
15
+ "2": "insult",
16
+ "3": "lgbtqphobia",
17
+ "4": "other_lifestyle",
18
+ "5": "physical_aspects",
19
+ "6": "profanity_obscene",
20
+ "7": "racism",
21
+ "8": "sexism",
22
+ "9": "xenophobia"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "health": 0,
28
+ "ideology": 1,
29
+ "insult": 2,
30
+ "lgbtqphobia": 3,
31
+ "other_lifestyle": 4,
32
+ "physical_aspects": 5,
33
+ "profanity_obscene": 6,
34
+ "racism": 7,
35
+ "sexism": 8,
36
+ "xenophobia": 9
37
+ },
38
+ "layer_norm_eps": 1e-12,
39
+ "max_position_embeddings": 512,
40
+ "model_type": "bert",
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 12,
43
+ "output_past": true,
44
+ "pad_token_id": 0,
45
+ "pooler_fc_size": 768,
46
+ "pooler_num_attention_heads": 12,
47
+ "pooler_num_fc_layers": 3,
48
+ "pooler_size_per_head": 128,
49
+ "pooler_type": "first_token_transform",
50
+ "position_embedding_type": "absolute",
51
+ "problem_type": "multi_label_classification",
52
+ "torch_dtype": "float32",
53
+ "transformers_version": "4.26.0",
54
+ "type_vocab_size": 2,
55
+ "use_cache": true,
56
+ "vocab_size": 29794
57
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:470d38b66827c19a1d4c2a4b878060407e7e469941dc6d11c87f9840fdace8d2
3
+ size 435794285
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "name_or_path": "neuralmind/bert-base-portuguese-cased",
8
+ "never_split": null,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--neuralmind--bert-base-portuguese-cased/snapshots/94d69c95f98f7d5b2a8700c420230ae10def0baa/special_tokens_map.json",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f239ffe8beb9c3a67f1d9767ba46f98222cf28146369ab269a52a840003fd55
3
+ size 3695
vocab.txt ADDED
The diff for this file is too large to render. See raw diff