Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +75 -0
- pytorch_model.bin +3 -0
- runs/Jul18_23-24-57_jordy-OMEN/1658179509.570703/events.out.tfevents.1658179509.jordy-OMEN.221106.1 +3 -0
- runs/Jul18_23-24-57_jordy-OMEN/events.out.tfevents.1658179509.jordy-OMEN.221106.0 +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
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "neuralmind/bert-base-portuguese-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
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": "O",
|
14 |
+
"1": "B-PESSOA",
|
15 |
+
"2": "I-PESSOA",
|
16 |
+
"3": "B-ORGANIZACAO",
|
17 |
+
"4": "I-ORGANIZACAO",
|
18 |
+
"5": "B-LOCAL",
|
19 |
+
"6": "I-LOCAL",
|
20 |
+
"7": "B-TEMPO",
|
21 |
+
"8": "I-TEMPO",
|
22 |
+
"9": "B-VALOR",
|
23 |
+
"10": "I-VALOR"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 3072,
|
27 |
+
"label2id": {
|
28 |
+
"B-LOCAL": 5,
|
29 |
+
"B-ORGANIZACAO": 3,
|
30 |
+
"B-PESSOA": 1,
|
31 |
+
"B-TEMPO": 7,
|
32 |
+
"B-VALOR": 9,
|
33 |
+
"I-LOCAL": 6,
|
34 |
+
"I-ORGANIZACAO": 4,
|
35 |
+
"I-PESSOA": 2,
|
36 |
+
"I-TEMPO": 8,
|
37 |
+
"I-VALOR": 10,
|
38 |
+
"O": 0
|
39 |
+
},
|
40 |
+
"layer_norm_eps": 1e-12,
|
41 |
+
"max_position_embeddings": 512,
|
42 |
+
"model_type": "bert",
|
43 |
+
"num_attention_heads": 12,
|
44 |
+
"num_hidden_layers": 12,
|
45 |
+
"output_past": true,
|
46 |
+
"pad_token_id": 0,
|
47 |
+
"pooler_fc_size": 768,
|
48 |
+
"pooler_num_attention_heads": 12,
|
49 |
+
"pooler_num_fc_layers": 3,
|
50 |
+
"pooler_size_per_head": 128,
|
51 |
+
"pooler_type": "first_token_transform",
|
52 |
+
"position_embedding_type": "absolute",
|
53 |
+
"test_args": {
|
54 |
+
"CRF": false,
|
55 |
+
"Y": "ner_tags",
|
56 |
+
"dataset": "harem",
|
57 |
+
"model": "neuralmind/bert-base-portuguese-cased",
|
58 |
+
"setting": "mini_harem",
|
59 |
+
"subset": "selective",
|
60 |
+
"subword_alignment": "first",
|
61 |
+
"task": "ner",
|
62 |
+
"train_args": {
|
63 |
+
"batch_size": 2,
|
64 |
+
"epochs": 3,
|
65 |
+
"learning_rate": 2e-05,
|
66 |
+
"warmup_ratio": 0.1,
|
67 |
+
"weight_decay": 0.01
|
68 |
+
}
|
69 |
+
},
|
70 |
+
"torch_dtype": "float32",
|
71 |
+
"transformers_version": "4.18.0",
|
72 |
+
"type_vocab_size": 2,
|
73 |
+
"use_cache": true,
|
74 |
+
"vocab_size": 29794
|
75 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:845b2ff8ebb5a8624a2e1c9c987fa7fce853da519442fbb64364ec0dab3b7f34
|
3 |
+
size 433434417
|
runs/Jul18_23-24-57_jordy-OMEN/1658179509.570703/events.out.tfevents.1658179509.jordy-OMEN.221106.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5940759050d44b099e8276d87417e3f457407cc78c38ee702aad61544d35dd9d
|
3 |
+
size 4931
|
runs/Jul18_23-24-57_jordy-OMEN/events.out.tfevents.1658179509.jordy-OMEN.221106.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:174988c0a63f8bdd4959432e1805f48b463e7379bb767983e538a9c802777450
|
3 |
+
size 5758
|
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/jordy/code/embeddings/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 sha256:085edbe52e6183dc2452c0272338d5e932a8c6b8f1e72e7ebfe5b2e51f8b1061
|
3 |
+
size 3119
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|