raulgdp commited on
Commit
76b7ab2
1 Parent(s): 7af49ac

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -22
README.md CHANGED
@@ -1,10 +1,9 @@
1
  ---
2
  license: apache-2.0
3
- base_model: bert-base-cased
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
- - conll2003
8
  metrics:
9
  - precision
10
  - recall
@@ -17,24 +16,24 @@ model-index:
17
  name: Token Classification
18
  type: token-classification
19
  dataset:
20
- name: conll2003
21
- type: conll2003
22
- config: conll2003
23
  split: validation
24
- args: conll2003
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.9276174773289365
29
  - name: Recall
30
  type: recall
31
- value: 0.9468192527768429
32
  - name: F1
33
  type: f1
34
- value: 0.9371200133255602
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9857979631482898
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -42,13 +41,13 @@ should probably proofread and complete it, then remove this comment. -->
42
 
43
  # bert-finetuned-ner
44
 
45
- This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.0566
48
- - Precision: 0.9276
49
- - Recall: 0.9468
50
- - F1: 0.9371
51
- - Accuracy: 0.9858
52
 
53
  ## Model description
54
 
@@ -79,14 +78,14 @@ The following hyperparameters were used during training:
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.2173 | 1.0 | 878 | 0.0741 | 0.8992 | 0.9281 | 0.9135 | 0.9803 |
83
- | 0.0449 | 2.0 | 1756 | 0.0580 | 0.9153 | 0.9398 | 0.9273 | 0.9844 |
84
- | 0.0268 | 3.0 | 2634 | 0.0566 | 0.9276 | 0.9468 | 0.9371 | 0.9858 |
85
 
86
 
87
  ### Framework versions
88
 
89
- - Transformers 4.32.0.dev0
90
- - Pytorch 2.0.1+cu117
91
- - Datasets 2.13.1
92
  - Tokenizers 0.13.3
 
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
  datasets:
6
+ - conll2002
7
  metrics:
8
  - precision
9
  - recall
 
16
  name: Token Classification
17
  type: token-classification
18
  dataset:
19
+ name: conll2002
20
+ type: conll2002
21
+ config: es
22
  split: validation
23
+ args: es
24
  metrics:
25
  - name: Precision
26
  type: precision
27
+ value: 0.8596766951055231
28
  - name: Recall
29
  type: recall
30
+ value: 0.8798253676470589
31
  - name: F1
32
  type: f1
33
+ value: 0.8696343402225755
34
  - name: Accuracy
35
  type: accuracy
36
+ value: 0.9784573574765641
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
41
 
42
  # bert-finetuned-ner
43
 
44
+ This model is a fine-tuned version of [BSC-LT/roberta-base-bne-capitel-ner](https://huggingface.co/BSC-LT/roberta-base-bne-capitel-ner) on the conll2002 dataset.
45
  It achieves the following results on the evaluation set:
46
+ - Loss: 0.0936
47
+ - Precision: 0.8597
48
+ - Recall: 0.8798
49
+ - F1: 0.8696
50
+ - Accuracy: 0.9785
51
 
52
  ## Model description
53
 
 
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | 0.1004 | 1.0 | 521 | 0.0850 | 0.8579 | 0.8821 | 0.8698 | 0.9782 |
82
+ | 0.0336 | 2.0 | 1042 | 0.0849 | 0.8584 | 0.8775 | 0.8679 | 0.9783 |
83
+ | 0.0197 | 3.0 | 1563 | 0.0936 | 0.8597 | 0.8798 | 0.8696 | 0.9785 |
84
 
85
 
86
  ### Framework versions
87
 
88
+ - Transformers 4.30.2
89
+ - Pytorch 2.0.0
90
+ - Datasets 2.1.0
91
  - Tokenizers 0.13.3