Hugging Face's logo

Luciano
/
bertimbau-base-lener-br-finetuned-lener-br

Token Classification
Transformers
PyTorch
TensorBoard
Safetensors
Portuguese
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
5
Luciano commited on
Commit
da5788f
•
1 Parent(s): 656e323

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +26 -26
README.md CHANGED
@@ -10,7 +10,7 @@ metrics:
10
  - f1
11
  - accuracy
12
  model-index:
13
- - name: bertimabau-base-lener-br-finetuned-lener-br
14
  results:
15
  - task:
16
  name: Token Classification
@@ -24,30 +24,30 @@ model-index:
24
  metrics:
25
  - name: Precision
26
  type: precision
27
- value: 0.8679441782961883
28
  - name: Recall
29
  type: recall
30
- value: 0.8961290322580645
31
  - name: F1
32
  type: f1
33
- value: 0.8818114485239656
34
  - name: Accuracy
35
  type: accuracy
36
- value: 0.9760769195605468
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
40
  should probably proofread and complete it, then remove this comment. -->
41
 
42
- # bertimabau-base-lener-br-finetuned-lener-br
43
 
44
- This model is a fine-tuned version of [Luciano/bert-base-portuguese-cased-finetuned-lener-br](https://huggingface.co/Luciano/bert-base-portuguese-cased-finetuned-lener-br) on the lener_br dataset.
45
  It achieves the following results on the evaluation set:
46
  - Loss: nan
47
- - Precision: 0.8679
48
- - Recall: 0.8961
49
- - F1: 0.8818
50
- - Accuracy: 0.9761
51
 
52
  ## Model description
53
 
@@ -78,21 +78,21 @@ The following hyperparameters were used during training:
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
- | 0.0706 | 1.0 | 1957 | nan | 0.8291 | 0.8460 | 0.8375 | 0.9660 |
82
- | 0.037 | 2.0 | 3914 | nan | 0.8403 | 0.8849 | 0.8621 | 0.9659 |
83
- | 0.0278 | 3.0 | 5871 | nan | 0.8470 | 0.9118 | 0.8782 | 0.9736 |
84
- | 0.0218 | 4.0 | 7828 | nan | 0.8429 | 0.8789 | 0.8605 | 0.9706 |
85
- | 0.0146 | 5.0 | 9785 | nan | 0.8216 | 0.9034 | 0.8606 | 0.9725 |
86
- | 0.0145 | 6.0 | 11742 | nan | 0.8552 | 0.8940 | 0.8741 | 0.9701 |
87
- | 0.0098 | 7.0 | 13699 | nan | 0.8697 | 0.9 | 0.8846 | 0.9752 |
88
- | 0.0074 | 8.0 | 15656 | nan | 0.8310 | 0.8862 | 0.8577 | 0.9655 |
89
- | 0.0053 | 9.0 | 17613 | nan | 0.8767 | 0.8852 | 0.8809 | 0.9738 |
90
- | 0.0035 | 10.0 | 19570 | nan | 0.8328 | 0.8796 | 0.8556 | 0.9714 |
91
- | 0.0029 | 11.0 | 21527 | nan | 0.8679 | 0.8974 | 0.8824 | 0.9746 |
92
- | 0.0014 | 12.0 | 23484 | nan | 0.8566 | 0.8813 | 0.8688 | 0.9735 |
93
- | 0.0021 | 13.0 | 25441 | nan | 0.8842 | 0.8880 | 0.8861 | 0.9754 |
94
- | 0.0031 | 14.0 | 27398 | nan | 0.8677 | 0.8987 | 0.8829 | 0.9762 |
95
- | 0.0008 | 15.0 | 29355 | nan | 0.8679 | 0.8961 | 0.8818 | 0.9761 |
96
 
97
 
98
  ### Framework versions
 
10
  - f1
11
  - accuracy
12
  model-index:
13
+ - name: bertimbau-base-lener-br-finetuned-lener-br
14
  results:
15
  - task:
16
  name: Token Classification
 
24
  metrics:
25
  - name: Precision
26
  type: precision
27
+ value: 0.8910105127655009
28
  - name: Recall
29
  type: recall
30
+ value: 0.8931182795698924
31
  - name: F1
32
  type: f1
33
+ value: 0.8920631511115884
34
  - name: Accuracy
35
  type: accuracy
36
+ value: 0.9770368903042955
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
40
  should probably proofread and complete it, then remove this comment. -->
41
 
42
+ # bertimbau-base-lener-br-finetuned-lener-br
43
 
44
+ This model is a fine-tuned version of [Luciano/bertimbau-base-finetuned-lener-br](https://huggingface.co/Luciano/bertimbau-base-finetuned-lener-br) on the lener_br dataset.
45
  It achieves the following results on the evaluation set:
46
  - Loss: nan
47
+ - Precision: 0.8910
48
+ - Recall: 0.8931
49
+ - F1: 0.8921
50
+ - Accuracy: 0.9770
51
 
52
  ## Model description
53
 
 
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | 0.0707 | 1.0 | 1957 | nan | 0.8435 | 0.8798 | 0.8613 | 0.9736 |
82
+ | 0.0374 | 2.0 | 3914 | nan | 0.8286 | 0.8533 | 0.8408 | 0.9670 |
83
+ | 0.0278 | 3.0 | 5871 | nan | 0.8635 | 0.9114 | 0.8868 | 0.9774 |
84
+ | 0.0223 | 4.0 | 7828 | nan | 0.9012 | 0.8714 | 0.8861 | 0.9780 |
85
+ | 0.0175 | 5.0 | 9785 | nan | 0.8598 | 0.9037 | 0.8812 | 0.9741 |
86
+ | 0.0105 | 6.0 | 11742 | nan | 0.8903 | 0.8671 | 0.8785 | 0.9746 |
87
+ | 0.0084 | 7.0 | 13699 | nan | 0.8864 | 0.9045 | 0.8954 | 0.9766 |
88
+ | 0.0093 | 8.0 | 15656 | nan | 0.8997 | 0.8935 | 0.8966 | 0.9790 |
89
+ | 0.0035 | 9.0 | 17613 | nan | 0.8901 | 0.8985 | 0.8943 | 0.9774 |
90
+ | 0.0031 | 10.0 | 19570 | nan | 0.8936 | 0.8955 | 0.8945 | 0.9773 |
91
+ | 0.0032 | 11.0 | 21527 | nan | 0.8848 | 0.8920 | 0.8884 | 0.9766 |
92
+ | 0.0009 | 12.0 | 23484 | nan | 0.8883 | 0.8914 | 0.8899 | 0.9769 |
93
+ | 0.0016 | 13.0 | 25441 | nan | 0.8868 | 0.8912 | 0.8890 | 0.9758 |
94
+ | 0.002 | 14.0 | 27398 | nan | 0.8920 | 0.8935 | 0.8928 | 0.9773 |
95
+ | 0.0008 | 15.0 | 29355 | nan | 0.8910 | 0.8931 | 0.8921 | 0.9770 |
96
 
97
 
98
  ### Framework versions