Luciano commited on
Commit
d4bc35b
1 Parent(s): be40872

Commit using trainer.push_to_hub()

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
README.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - lener_br
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model_index:
13
+ - name: bertimbau-base-lener_br
14
+ results:
15
+ - task:
16
+ name: Token Classification
17
+ type: token-classification
18
+ dataset:
19
+ name: lener_br
20
+ type: lener_br
21
+ args: lener_br
22
+ metric:
23
+ name: Accuracy
24
+ type: accuracy
25
+ value: 0.9692504609383333
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # bertimbau-base-lener_br
32
+
33
+ This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on the lener_br dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.2298
36
+ - Precision: 0.8501
37
+ - Recall: 0.9138
38
+ - F1: 0.8808
39
+ - Accuracy: 0.9693
40
+
41
+ ## Model description
42
+
43
+ More information needed
44
+
45
+ ## Intended uses & limitations
46
+
47
+ More information needed
48
+
49
+ ## Training and evaluation data
50
+
51
+ More information needed
52
+
53
+ ## Training procedure
54
+
55
+ ### Training hyperparameters
56
+
57
+ The following hyperparameters were used during training:
58
+ - learning_rate: 2e-05
59
+ - train_batch_size: 4
60
+ - eval_batch_size: 4
61
+ - seed: 42
62
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
+ - lr_scheduler_type: linear
64
+ - num_epochs: 15
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
69
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
70
+ | 0.0686 | 1.0 | 1957 | 0.1399 | 0.7759 | 0.8669 | 0.8189 | 0.9641 |
71
+ | 0.0437 | 2.0 | 3914 | 0.1457 | 0.7997 | 0.8938 | 0.8441 | 0.9623 |
72
+ | 0.0313 | 3.0 | 5871 | 0.1675 | 0.8466 | 0.8744 | 0.8603 | 0.9651 |
73
+ | 0.0201 | 4.0 | 7828 | 0.1621 | 0.8713 | 0.8839 | 0.8775 | 0.9718 |
74
+ | 0.0137 | 5.0 | 9785 | 0.1811 | 0.7783 | 0.9159 | 0.8415 | 0.9645 |
75
+ | 0.0105 | 6.0 | 11742 | 0.1836 | 0.8568 | 0.9009 | 0.8783 | 0.9692 |
76
+ | 0.0105 | 7.0 | 13699 | 0.1649 | 0.8339 | 0.9125 | 0.8714 | 0.9725 |
77
+ | 0.0059 | 8.0 | 15656 | 0.2298 | 0.8501 | 0.9138 | 0.8808 | 0.9693 |
78
+ | 0.0051 | 9.0 | 17613 | 0.2210 | 0.8437 | 0.9045 | 0.8731 | 0.9693 |
79
+ | 0.0061 | 10.0 | 19570 | 0.2499 | 0.8627 | 0.8946 | 0.8784 | 0.9681 |
80
+ | 0.0041 | 11.0 | 21527 | 0.1985 | 0.8560 | 0.9052 | 0.8799 | 0.9720 |
81
+ | 0.003 | 12.0 | 23484 | 0.2204 | 0.8498 | 0.9065 | 0.8772 | 0.9699 |
82
+ | 0.0014 | 13.0 | 25441 | 0.2152 | 0.8425 | 0.9067 | 0.8734 | 0.9709 |
83
+ | 0.0005 | 14.0 | 27398 | 0.2317 | 0.8553 | 0.8987 | 0.8765 | 0.9705 |
84
+ | 0.0015 | 15.0 | 29355 | 0.2436 | 0.8543 | 0.8989 | 0.8760 | 0.9700 |
85
+
86
+
87
+ ### Framework versions
88
+
89
+ - Transformers 4.8.2
90
+ - Pytorch 1.9.0+cu102
91
+ - Datasets 1.9.0
92
+ - Tokenizers 0.10.3
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "neuralmind/bert-base-portuguese-cased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "directionality": "bidi",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-ORGANIZACAO",
15
+ "2": "I-ORGANIZACAO",
16
+ "3": "B-PESSOA",
17
+ "4": "I-PESSOA",
18
+ "5": "B-TEMPO",
19
+ "6": "I-TEMPO",
20
+ "7": "B-LOCAL",
21
+ "8": "I-LOCAL",
22
+ "9": "B-LEGISLACAO",
23
+ "10": "I-LEGISLACAO",
24
+ "11": "B-JURISPRUDENCIA",
25
+ "12": "I-JURISPRUDENCIA"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 3072,
29
+ "label2id": {
30
+ "B-JURISPRUDENCIA": 11,
31
+ "B-LEGISLACAO": 9,
32
+ "B-LOCAL": 7,
33
+ "B-ORGANIZACAO": 1,
34
+ "B-PESSOA": 3,
35
+ "B-TEMPO": 5,
36
+ "I-JURISPRUDENCIA": 12,
37
+ "I-LEGISLACAO": 10,
38
+ "I-LOCAL": 8,
39
+ "I-ORGANIZACAO": 2,
40
+ "I-PESSOA": 4,
41
+ "I-TEMPO": 6,
42
+ "O": 0
43
+ },
44
+ "layer_norm_eps": 1e-12,
45
+ "max_position_embeddings": 512,
46
+ "model_type": "bert",
47
+ "num_attention_heads": 12,
48
+ "num_hidden_layers": 12,
49
+ "output_past": true,
50
+ "pad_token_id": 0,
51
+ "pooler_fc_size": 768,
52
+ "pooler_num_attention_heads": 12,
53
+ "pooler_num_fc_layers": 3,
54
+ "pooler_size_per_head": 128,
55
+ "pooler_type": "first_token_transform",
56
+ "position_embedding_type": "absolute",
57
+ "transformers_version": "4.8.2",
58
+ "type_vocab_size": 2,
59
+ "use_cache": true,
60
+ "vocab_size": 29794
61
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d488202ac3fe766f991ffb7f04eaf587b1bba28202705a4eeb6ae914f094e45e
3
+ size 433453553
runs/Jul13_14-49-26_c88825540bf2/1626187774.517446/events.out.tfevents.1626187774.c88825540bf2.75.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa2dc3f10e0fd32f0e8b1bf8edf7ef2f59b00a95aac53625be8a5054aae32bdb
3
+ size 4234
runs/Jul13_14-49-26_c88825540bf2/events.out.tfevents.1626187774.c88825540bf2.75.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e830b8154758dafb8e2b6fcb08a1260bb437e2992bfb35dfb8d0821b1e70e2b
3
+ size 20488
runs/Jul13_14-49-26_c88825540bf2/events.out.tfevents.1626190101.c88825540bf2.75.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5f685ba276eb9b722da8af44c9d131c18c485af975410224c0257aa39cfbcbe
3
+ size 521
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, "model_max_length": 512, "special_tokens_map_file": "/root/.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:bb08c5e56cd3860de724efd57330ca7d09377a26f5b04ce713c574a9abeb3cdb
3
+ size 2671
vocab.txt ADDED
The diff for this file is too large to render. See raw diff