flavio-nakasato
commited on
Commit
•
67d4f65
1
Parent(s):
be7c5cf
First commit
Browse files- README.md +1 -0
- config.json +33 -0
- pytorch_model.bin +3 -0
- runs/Aug15_04-17-34_ciaamS03/1629011860.3545313/events.out.tfevents.1629011860.ciaamS03.6622.1 +3 -0
- runs/Aug15_04-17-34_ciaamS03/events.out.tfevents.1629011860.ciaamS03.6622.0 +3 -0
- runs/Aug15_04-18-21_ciaamS03/1629011901.7950382/events.out.tfevents.1629011901.ciaamS03.6622.3 +3 -0
- runs/Aug15_04-18-21_ciaamS03/events.out.tfevents.1629011901.ciaamS03.6622.2 +3 -0
- runs/Aug15_04-18-30_ciaamS03/1629011910.2649357/events.out.tfevents.1629011910.ciaamS03.6622.5 +3 -0
- runs/Aug15_04-18-30_ciaamS03/events.out.tfevents.1629011910.ciaamS03.6622.4 +3 -0
- runs/Aug15_04-18-46_ciaamS03/1629011926.6045406/events.out.tfevents.1629011926.ciaamS03.6622.7 +3 -0
- runs/Aug15_04-18-46_ciaamS03/events.out.tfevents.1629011926.ciaamS03.6622.6 +3 -0
- runs/Aug15_04-21-21_ciaamS03/1629012086.505279/events.out.tfevents.1629012086.ciaamS03.7131.1 +3 -0
- runs/Aug15_04-21-21_ciaamS03/events.out.tfevents.1629012086.ciaamS03.7131.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
MLM fine-tuned from Bertimbau-Base model on the Brazilian Federal Official Gazette (500k instances)
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "neuralmind/bert-base-portuguese-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-12,
|
16 |
+
"max_position_embeddings": 512,
|
17 |
+
"model_type": "bert",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"pooler_fc_size": 768,
|
23 |
+
"pooler_num_attention_heads": 12,
|
24 |
+
"pooler_num_fc_layers": 3,
|
25 |
+
"pooler_size_per_head": 128,
|
26 |
+
"pooler_type": "first_token_transform",
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.10.0.dev0",
|
30 |
+
"type_vocab_size": 2,
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 29794
|
33 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2184dc03c7f4cb979ee0eadebfe799645c704370f3d5f6d572ce4cfe896e31a3
|
3 |
+
size 435902699
|
runs/Aug15_04-17-34_ciaamS03/1629011860.3545313/events.out.tfevents.1629011860.ciaamS03.6622.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31975bb8c8e3ed8434ea7915e42b047d01d25d8c00c97fff23224d2980cce30f
|
3 |
+
size 4174
|
runs/Aug15_04-17-34_ciaamS03/events.out.tfevents.1629011860.ciaamS03.6622.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce41488ecf4d24389b016cfaf95d5c5198df06646f363bc2f9196d05515573c6
|
3 |
+
size 40
|
runs/Aug15_04-18-21_ciaamS03/1629011901.7950382/events.out.tfevents.1629011901.ciaamS03.6622.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6617787cc15ae99c5642ea9caed48a2bab040fab1cd77dae40f74d35a27a9230
|
3 |
+
size 4174
|
runs/Aug15_04-18-21_ciaamS03/events.out.tfevents.1629011901.ciaamS03.6622.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a919951a8c9bf994881eb7c52749ce7c9c58e3d6dd0b81b798420e11a25a6c22
|
3 |
+
size 40
|
runs/Aug15_04-18-30_ciaamS03/1629011910.2649357/events.out.tfevents.1629011910.ciaamS03.6622.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dac4ce03f32610760444d66b962e4b40c335e73ba84fe845d1fda319fd3c5ebe
|
3 |
+
size 4174
|
runs/Aug15_04-18-30_ciaamS03/events.out.tfevents.1629011910.ciaamS03.6622.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:465bd282260581d7ca0b08625c9c1f250950c1519ba926dae49c8e28b9e61227
|
3 |
+
size 40
|
runs/Aug15_04-18-46_ciaamS03/1629011926.6045406/events.out.tfevents.1629011926.ciaamS03.6622.7
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99ba7eebeee4c11e1d873e1e3ec1b8404d72248c017023f762b461436d013f61
|
3 |
+
size 4174
|
runs/Aug15_04-18-46_ciaamS03/events.out.tfevents.1629011926.ciaamS03.6622.6
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91bb1136985a5cd73795a9f503578bcc9cfd6f674bb0bfbdb77c028c20fbdc7d
|
3 |
+
size 40
|
runs/Aug15_04-21-21_ciaamS03/1629012086.505279/events.out.tfevents.1629012086.ciaamS03.7131.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b50692e2be98af09b1da4d2e7e433b4a4092626f4c69efe44b3346999cebd4d9
|
3 |
+
size 4174
|
runs/Aug15_04-21-21_ciaamS03/events.out.tfevents.1629012086.ciaamS03.7131.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2659459e96e0b65aa7bb6161dae1b03560e03acc28e75e1dcfd59203597b7893
|
3 |
+
size 6510
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/home/flavionakasato/.cache/huggingface/transformers/eecc45187d085a1169eed91017d358cc0e9cbdd5dc236bcd710059dbf0a2f816.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "neuralmind/bert-base-portuguese-cased", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:655a55c81fb1c9b8387549fb3b901917462e28038a8737b6ff0d1d095f0733f2
|
3 |
+
size 2607
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|