ricardo-filho commited on
Commit
1a37cac
1 Parent(s): c89fc88

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -22
README.md CHANGED
@@ -14,34 +14,34 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.0328
18
- - Criterio Julgamento Precision: 0.675
19
- - Criterio Julgamento Recall: 0.7788
20
- - Criterio Julgamento F1: 0.7232
21
  - Criterio Julgamento Number: 104
22
- - Data Sessao Precision: 0.6604
23
- - Data Sessao Recall: 0.6364
24
- - Data Sessao F1: 0.6481
25
  - Data Sessao Number: 55
26
- - Modalidade Licitacao Precision: 0.9263
27
- - Modalidade Licitacao Recall: 0.9549
28
- - Modalidade Licitacao F1: 0.9404
29
  - Modalidade Licitacao Number: 421
30
- - Numero Exercicio Precision: 0.8535
31
- - Numero Exercicio Recall: 0.9135
32
- - Numero Exercicio F1: 0.8825
33
  - Numero Exercicio Number: 185
34
- - Objeto Licitacao Precision: 0.2471
35
- - Objeto Licitacao Recall: 0.3559
36
- - Objeto Licitacao F1: 0.2917
37
  - Objeto Licitacao Number: 59
38
- - Valor Objeto Precision: 0.5091
39
- - Valor Objeto Recall: 0.6829
40
- - Valor Objeto F1: 0.5833
41
  - Valor Objeto Number: 41
42
- - Overall Precision: 0.7788
43
- - Overall Recall: 0.8509
44
- - Overall F1: 0.8133
45
  - Overall Accuracy: 0.9948
46
 
47
  ## Model description
 
14
 
15
  This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) on an unknown dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.0192
18
+ - Criterio Julgamento Precision: 0.7209
19
+ - Criterio Julgamento Recall: 0.8942
20
+ - Criterio Julgamento F1: 0.7983
21
  - Criterio Julgamento Number: 104
22
+ - Data Sessao Precision: 0.6351
23
+ - Data Sessao Recall: 0.8545
24
+ - Data Sessao F1: 0.7287
25
  - Data Sessao Number: 55
26
+ - Modalidade Licitacao Precision: 0.9224
27
+ - Modalidade Licitacao Recall: 0.9596
28
+ - Modalidade Licitacao F1: 0.9406
29
  - Modalidade Licitacao Number: 421
30
+ - Numero Exercicio Precision: 0.8872
31
+ - Numero Exercicio Recall: 0.9351
32
+ - Numero Exercicio F1: 0.9105
33
  - Numero Exercicio Number: 185
34
+ - Objeto Licitacao Precision: 0.2348
35
+ - Objeto Licitacao Recall: 0.4576
36
+ - Objeto Licitacao F1: 0.3103
37
  - Objeto Licitacao Number: 59
38
+ - Valor Objeto Precision: 0.5424
39
+ - Valor Objeto Recall: 0.7805
40
+ - Valor Objeto F1: 0.64
41
  - Valor Objeto Number: 41
42
+ - Overall Precision: 0.7683
43
+ - Overall Recall: 0.8971
44
+ - Overall F1: 0.8277
45
  - Overall Accuracy: 0.9948
46
 
47
  ## Model description