Hugging Face's logo

Yv
/
bert-finetuned-ner

Token Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
3
Yv commited on
Commit
7317243
·
1 Parent(s): 4cff1c0

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -14
README.md CHANGED
@@ -22,16 +22,16 @@ model-index:
22
  metrics:
23
  - name: Precision
24
  type: precision
25
- value: 0.93488679557098
26
  - name: Recall
27
  type: recall
28
- value: 0.9520363513968361
29
  - name: F1
30
  type: f1
31
- value: 0.9433836404569332
32
  - name: Accuracy
33
  type: accuracy
34
- value: 0.9864160828869135
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,11 +41,11 @@ should probably proofread and complete it, then remove this comment. -->
41
 
42
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
43
  It achieves the following results on the evaluation set:
44
- - Loss: 0.0610
45
- - Precision: 0.9349
46
- - Recall: 0.9520
47
- - F1: 0.9434
48
- - Accuracy: 0.9864
49
 
50
  ## Model description
51
 
@@ -76,14 +76,14 @@ The following hyperparameters were used during training:
76
 
77
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
78
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
79
- | 0.0881 | 1.0 | 1756 | 0.0653 | 0.9175 | 0.9364 | 0.9269 | 0.9829 |
80
- | 0.0379 | 2.0 | 3512 | 0.0607 | 0.9360 | 0.9483 | 0.9422 | 0.9861 |
81
- | 0.0204 | 3.0 | 5268 | 0.0610 | 0.9349 | 0.9520 | 0.9434 | 0.9864 |
82
 
83
 
84
  ### Framework versions
85
 
86
- - Transformers 4.14.1
87
  - Pytorch 1.10.0+cu111
88
- - Datasets 1.16.1
89
  - Tokenizers 0.10.3
 
22
  metrics:
23
  - name: Precision
24
  type: precision
25
+ value: 0.9369817578772802
26
  - name: Recall
27
  type: recall
28
+ value: 0.9508582968697409
29
  - name: F1
30
  type: f1
31
+ value: 0.9438690277313732
32
  - name: Accuracy
33
  type: accuracy
34
+ value: 0.9868575969859305
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
41
 
42
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
43
  It achieves the following results on the evaluation set:
44
+ - Loss: 0.0598
45
+ - Precision: 0.9370
46
+ - Recall: 0.9509
47
+ - F1: 0.9439
48
+ - Accuracy: 0.9869
49
 
50
  ## Model description
51
 
 
76
 
77
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
78
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
79
+ | 0.0871 | 1.0 | 1756 | 0.0633 | 0.9197 | 0.9362 | 0.9279 | 0.9833 |
80
+ | 0.0386 | 2.0 | 3512 | 0.0572 | 0.9351 | 0.9483 | 0.9417 | 0.9866 |
81
+ | 0.0214 | 3.0 | 5268 | 0.0598 | 0.9370 | 0.9509 | 0.9439 | 0.9869 |
82
 
83
 
84
  ### Framework versions
85
 
86
+ - Transformers 4.15.0
87
  - Pytorch 1.10.0+cu111
88
+ - Datasets 1.17.0
89
  - Tokenizers 0.10.3