ricardo-filho commited on
Commit
e6defd6
1 Parent(s): 46f6f37

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -21
README.md CHANGED
@@ -14,35 +14,35 @@ 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: 0.0295
18
- - Criterio Julgamento Precision: 0.8488
19
- - Criterio Julgamento Recall: 0.8902
20
- - Criterio Julgamento F1: 0.8690
21
  - Criterio Julgamento Number: 82
22
- - Data Sessao Precision: 0.7903
23
- - Data Sessao Recall: 0.8909
24
- - Data Sessao F1: 0.8376
25
  - Data Sessao Number: 55
26
- - Modalidade Licitacao Precision: 0.9571
27
- - Modalidade Licitacao Recall: 0.9781
28
- - Modalidade Licitacao F1: 0.9674
29
  - Modalidade Licitacao Number: 319
30
- - Numero Exercicio Precision: 0.9181
31
- - Numero Exercicio Recall: 0.9812
32
- - Numero Exercicio F1: 0.9486
33
  - Numero Exercicio Number: 160
34
- - Objeto Licitacao Precision: 0.6393
35
- - Objeto Licitacao Recall: 0.6724
36
- - Objeto Licitacao F1: 0.6555
37
  - Objeto Licitacao Number: 58
38
- - Valor Objeto Precision: 0.9211
39
  - Valor Objeto Recall: 0.9211
40
- - Valor Objeto F1: 0.9211
41
  - Valor Objeto Number: 38
42
- - Overall Precision: 0.8938
43
  - Overall Recall: 0.9340
44
- - Overall F1: 0.9135
45
- - Overall Accuracy: 0.9962
46
 
47
  ## Model description
48
 
 
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: 0.0193
18
+ - Criterio Julgamento Precision: 0.8875
19
+ - Criterio Julgamento Recall: 0.8659
20
+ - Criterio Julgamento F1: 0.8765
21
  - Criterio Julgamento Number: 82
22
+ - Data Sessao Precision: 0.7571
23
+ - Data Sessao Recall: 0.9636
24
+ - Data Sessao F1: 0.848
25
  - Data Sessao Number: 55
26
+ - Modalidade Licitacao Precision: 0.9394
27
+ - Modalidade Licitacao Recall: 0.9718
28
+ - Modalidade Licitacao F1: 0.9553
29
  - Modalidade Licitacao Number: 319
30
+ - Numero Exercicio Precision: 0.9172
31
+ - Numero Exercicio Recall: 0.9688
32
+ - Numero Exercicio F1: 0.9422
33
  - Numero Exercicio Number: 160
34
+ - Objeto Licitacao Precision: 0.4659
35
+ - Objeto Licitacao Recall: 0.7069
36
+ - Objeto Licitacao F1: 0.5616
37
  - Objeto Licitacao Number: 58
38
+ - Valor Objeto Precision: 0.8333
39
  - Valor Objeto Recall: 0.9211
40
+ - Valor Objeto F1: 0.875
41
  - Valor Objeto Number: 38
42
+ - Overall Precision: 0.8537
43
  - Overall Recall: 0.9340
44
+ - Overall F1: 0.8920
45
+ - Overall Accuracy: 0.9951
46
 
47
  ## Model description
48