MattosDev commited on
Commit
69490b1
·
verified ·
1 Parent(s): 9f17da6

Retreino automático via pipeline Foxy

Browse files
Files changed (5) hide show
  1. README.md +19 -81
  2. config.json +22 -24
  3. model.safetensors +2 -2
  4. tokenizer.json +16 -2
  5. training_args.bin +2 -2
README.md CHANGED
@@ -1,87 +1,25 @@
1
  ---
2
- library_name: transformers
3
- license: mit
4
- base_model: neuralmind/bert-large-portuguese-cased
5
  tags:
6
- - generated_from_trainer
7
- metrics:
8
- - accuracy
9
- model-index:
10
- - name: foxy-nlp-br
11
- results: []
12
  ---
13
 
14
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
- should probably proofread and complete it, then remove this comment. -->
16
 
17
- # foxy-nlp-br
18
 
19
- This model is a fine-tuned version of [neuralmind/bert-large-portuguese-cased](https://huggingface.co/neuralmind/bert-large-portuguese-cased) on the None dataset.
20
- It achieves the following results on the evaluation set:
21
- - Loss: 0.1638
22
- - Accuracy: 0.9714
23
- - F1 Weighted: 0.9714
24
- - F1 Macro: 0.9740
25
- - F1 Saudacao: 1.0
26
- - F1 Cancelamento: 1.0
27
- - F1 Reclamacao: 0.8824
28
- - F1 Financeiro: 1.0
29
- - F1 Suporte Tecnico: 0.9545
30
- - F1 Elogio: 0.9412
31
- - F1 Informacao: 1.0
32
- - F1 Pedido Entrega: 1.0
33
- - F1 Conta Perfil: 0.9615
34
- - F1 Negociacao Retencao: 1.0
35
- - F1 Min Class: 0.8824
36
-
37
- ## Model description
38
-
39
- More information needed
40
-
41
- ## Intended uses & limitations
42
-
43
- More information needed
44
-
45
- ## Training and evaluation data
46
-
47
- More information needed
48
-
49
- ## Training procedure
50
-
51
- ### Training hyperparameters
52
-
53
- The following hyperparameters were used during training:
54
- - learning_rate: 4.197342969974621e-05
55
- - train_batch_size: 16
56
- - eval_batch_size: 8
57
- - seed: 42
58
- - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
59
- - lr_scheduler_type: linear
60
- - lr_scheduler_warmup_steps: 0.0022118889184775006
61
- - num_epochs: 22
62
-
63
- ### Training results
64
-
65
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Weighted | F1 Macro | F1 Saudacao | F1 Cancelamento | F1 Reclamacao | F1 Financeiro | F1 Suporte Tecnico | F1 Elogio | F1 Informacao | F1 Pedido Entrega | F1 Conta Perfil | F1 Negociacao Retencao | F1 Min Class |
66
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:-----------:|:--------:|:-----------:|:---------------:|:-------------:|:-------------:|:------------------:|:---------:|:-------------:|:-----------------:|:---------------:|:----------------------:|:------------:|
67
- | 0.8071 | 1.0 | 125 | 0.8255 | 0.7943 | 0.7724 | 0.7549 | 0.8966 | 0.7059 | 0.7692 | 0.7619 | 0.8261 | 0.9143 | 0.75 | 0.9375 | 0.8333 | 0.1538 | 0.1538 |
68
- | 0.2542 | 2.0 | 250 | 0.3204 | 0.9257 | 0.9254 | 0.9301 | 0.9630 | 0.9714 | 0.8824 | 1.0 | 0.8837 | 0.9412 | 0.8421 | 0.9375 | 0.9231 | 0.9565 | 0.8421 |
69
- | 0.0880 | 3.0 | 375 | 0.2739 | 0.9314 | 0.9306 | 0.9334 | 0.9286 | 1.0 | 0.8824 | 1.0 | 0.9048 | 0.9412 | 0.8571 | 0.9375 | 0.9259 | 0.9565 | 0.8571 |
70
- | 0.0176 | 4.0 | 500 | 0.2407 | 0.9486 | 0.9482 | 0.9519 | 1.0 | 1.0 | 0.8824 | 1.0 | 0.9048 | 0.9412 | 0.9231 | 0.9677 | 0.9434 | 0.9565 | 0.8824 |
71
- | 0.0129 | 5.0 | 625 | 0.2209 | 0.9543 | 0.9541 | 0.9563 | 1.0 | 1.0 | 0.8824 | 1.0 | 0.9302 | 0.9412 | 0.9231 | 0.9677 | 0.9615 | 0.9565 | 0.8824 |
72
- | 0.0072 | 6.0 | 750 | 0.2345 | 0.9543 | 0.9541 | 0.9569 | 1.0 | 1.0 | 0.8824 | 1.0 | 0.9302 | 0.9412 | 0.9474 | 0.9677 | 0.9434 | 0.9565 | 0.8824 |
73
- | 0.0085 | 7.0 | 875 | 0.2161 | 0.96 | 0.9599 | 0.9638 | 1.0 | 1.0 | 0.8824 | 1.0 | 0.9302 | 0.9412 | 0.9730 | 0.9677 | 0.9434 | 1.0 | 0.8824 |
74
- | 0.0061 | 8.0 | 1000 | 0.2211 | 0.96 | 0.9599 | 0.9638 | 1.0 | 1.0 | 0.8824 | 1.0 | 0.9302 | 0.9412 | 0.9730 | 0.9677 | 0.9434 | 1.0 | 0.8824 |
75
- | 0.0076 | 9.0 | 1125 | 0.1966 | 0.96 | 0.9599 | 0.9638 | 1.0 | 1.0 | 0.8824 | 1.0 | 0.9302 | 0.9412 | 0.9730 | 0.9677 | 0.9434 | 1.0 | 0.8824 |
76
- | 0.0053 | 10.0 | 1250 | 0.1642 | 0.9714 | 0.9714 | 0.9740 | 1.0 | 1.0 | 0.8824 | 1.0 | 0.9545 | 0.9412 | 1.0 | 1.0 | 0.9615 | 1.0 | 0.8824 |
77
- | 0.0069 | 11.0 | 1375 | 0.1517 | 0.9657 | 0.9657 | 0.9680 | 1.0 | 1.0 | 0.8824 | 1.0 | 0.9545 | 0.9412 | 0.9730 | 0.9677 | 0.9615 | 1.0 | 0.8824 |
78
- | 0.0049 | 12.0 | 1500 | 0.1775 | 0.96 | 0.9599 | 0.9638 | 1.0 | 1.0 | 0.8824 | 1.0 | 0.9302 | 0.9412 | 0.9730 | 0.9677 | 0.9434 | 1.0 | 0.8824 |
79
- | 0.0051 | 13.0 | 1625 | 0.1730 | 0.9657 | 0.9657 | 0.9680 | 1.0 | 1.0 | 0.8824 | 1.0 | 0.9545 | 0.9412 | 0.9730 | 0.9677 | 0.9615 | 1.0 | 0.8824 |
80
-
81
-
82
- ### Framework versions
83
-
84
- - Transformers 5.3.0
85
- - Pytorch 2.10.0+cu128
86
- - Datasets 3.0.0
87
- - Tokenizers 0.22.2
 
1
  ---
2
+ language: pt
3
+ license: apache-2.0
4
+ pipeline_tag: text-classification
5
  tags:
6
+ - portuguese
7
+ - text-classification
8
+ - customer-support
9
+ - foxy
 
 
10
  ---
11
 
12
+ # Foxy NLP BR
 
13
 
14
+ Modelo de classificação de intenções treinado para roteamento N1 e extração de dados.
15
 
16
+ ## Labels Identificadas no Treino:
17
+ - `CANCELAMENTO`
18
+ - `CONTA_PERFIL`
19
+ - `ELOGIO`
20
+ - `FINANCEIRO`
21
+ - `INFORMACAO`
22
+ - `PEDIDO_ENTREGA`
23
+ - `RECLAMACAO`
24
+ - `SAUDACAO`
25
+ - `SUPORTE_TECNICO`
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json CHANGED
@@ -7,43 +7,41 @@
7
  "bos_token_id": null,
8
  "classifier_dropout": null,
9
  "directionality": "bidi",
10
- "dtype": "bfloat16",
11
  "eos_token_id": null,
12
  "hidden_act": "gelu",
13
  "hidden_dropout_prob": 0.1,
14
- "hidden_size": 1024,
15
  "id2label": {
16
- "0": "SAUDACAO",
17
- "1": "CANCELAMENTO",
18
- "2": "RECLAMACAO",
19
  "3": "FINANCEIRO",
20
- "4": "SUPORTE_TECNICO",
21
- "5": "ELOGIO",
22
- "6": "INFORMACAO",
23
- "7": "PEDIDO_ENTREGA",
24
- "8": "CONTA_PERFIL",
25
- "9": "NEGOCIACAO_RETENCAO"
26
  },
27
  "initializer_range": 0.02,
28
- "intermediate_size": 4096,
29
  "is_decoder": false,
30
  "label2id": {
31
- "CANCELAMENTO": 1,
32
- "CONTA_PERFIL": 8,
33
- "ELOGIO": 5,
34
  "FINANCEIRO": 3,
35
- "INFORMACAO": 6,
36
- "NEGOCIACAO_RETENCAO": 9,
37
- "PEDIDO_ENTREGA": 7,
38
- "RECLAMACAO": 2,
39
- "SAUDACAO": 0,
40
- "SUPORTE_TECNICO": 4
41
  },
42
  "layer_norm_eps": 1e-12,
43
  "max_position_embeddings": 512,
44
  "model_type": "bert",
45
- "num_attention_heads": 16,
46
- "num_hidden_layers": 24,
47
  "output_past": true,
48
  "pad_token_id": 0,
49
  "pooler_fc_size": 768,
@@ -53,7 +51,7 @@
53
  "pooler_type": "first_token_transform",
54
  "problem_type": "single_label_classification",
55
  "tie_word_embeddings": true,
56
- "transformers_version": "5.3.0",
57
  "type_vocab_size": 2,
58
  "use_cache": false,
59
  "vocab_size": 29794
 
7
  "bos_token_id": null,
8
  "classifier_dropout": null,
9
  "directionality": "bidi",
10
+ "dtype": "float32",
11
  "eos_token_id": null,
12
  "hidden_act": "gelu",
13
  "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
  "id2label": {
16
+ "0": "CANCELAMENTO",
17
+ "1": "CONTA_PERFIL",
18
+ "2": "ELOGIO",
19
  "3": "FINANCEIRO",
20
+ "4": "INFORMACAO",
21
+ "5": "PEDIDO_ENTREGA",
22
+ "6": "RECLAMACAO",
23
+ "7": "SAUDACAO",
24
+ "8": "SUPORTE_TECNICO"
 
25
  },
26
  "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
  "is_decoder": false,
29
  "label2id": {
30
+ "CANCELAMENTO": 0,
31
+ "CONTA_PERFIL": 1,
32
+ "ELOGIO": 2,
33
  "FINANCEIRO": 3,
34
+ "INFORMACAO": 4,
35
+ "PEDIDO_ENTREGA": 5,
36
+ "RECLAMACAO": 6,
37
+ "SAUDACAO": 7,
38
+ "SUPORTE_TECNICO": 8
 
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,
 
51
  "pooler_type": "first_token_transform",
52
  "problem_type": "single_label_classification",
53
  "tie_word_embeddings": true,
54
+ "transformers_version": "5.0.0",
55
  "type_vocab_size": 2,
56
  "use_cache": false,
57
  "vocab_size": 29794
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c844ae87e6d8bcc30cfd0ac44be8d5646339e140379fdfe7a29123668e64f80
3
- size 668860420
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69176e9b302ee2c6ed9bbe45587f44b36bc91ce28620e0e9abfb0bde4e9bfd4f
3
+ size 435743732
tokenizer.json CHANGED
@@ -1,7 +1,21 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 128,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 128
12
+ },
13
+ "direction": "Right",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 0,
16
+ "pad_type_id": 0,
17
+ "pad_token": "[PAD]"
18
+ },
19
  "added_tokens": [
20
  {
21
  "id": 0,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1523987fb11f96d5f9556324310fb96ac62b5249b411b414ee81c0c554680111
3
- size 5265
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db048dd129bb12446d1f54b61d4c4adfba4e3956c7d13fecb40b73ad63539b9c
3
+ size 5201