Tiago Barbosa de Lima commited on
Commit
0dd050e
·
1 Parent(s): 5dabc6f

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "neuralmind/bert-large-portuguese-cased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "finetuning_task": "ner",
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "I-COMMA",
15
+ "1": "I-PERIOD",
16
+ "2": "O"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "I-COMMA": 0,
22
+ "I-PERIOD": 1,
23
+ "O": 2
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 24,
30
+ "output_past": true,
31
+ "pad_token_id": 0,
32
+ "pooler_fc_size": 768,
33
+ "pooler_num_attention_heads": 12,
34
+ "pooler_num_fc_layers": 3,
35
+ "pooler_size_per_head": 128,
36
+ "pooler_type": "first_token_transform",
37
+ "position_embedding_type": "absolute",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.24.0",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 29794
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ac171bd5f7b294dc0d999df41570dd3b3ec034bef60f62dbcd636d253efe03
3
+ size 1333534897
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "name_or_path": "neuralmind/bert-large-portuguese-cased",
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": "/root/.cache/huggingface/hub/models--neuralmind--bert-large-portuguese-cased/snapshots/aa302f6ea73b759f7df9cad58bd272127b67ec28/special_tokens_map.json",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4a16e4a6edd3f1196e673e04ead0fda142a158f0eefc2a9f1f139c4bd67553a
3
+ size 3503
vocab.txt ADDED
The diff for this file is too large to render. See raw diff