Hugging Face's logo

chandrasutrisnotjhong
/
bert-finetuned-ner

Token Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
chandrasutrisnotjhong commited on
Commit
4513622
•
1 Parent(s): 795a640

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -22,16 +22,16 @@ model-index:
22
  metrics:
23
  - name: Precision
24
  type: precision
25
- value: 0.9332231404958677
26
  - name: Recall
27
  type: recall
28
- value: 0.9501851228542578
29
  - name: F1
30
  type: f1
31
- value: 0.9416277518345565
32
  - name: Accuracy
33
  type: accuracy
34
- value: 0.9859892859245305
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: 0.0611
45
- - Precision: 0.9332
46
- - Recall: 0.9502
47
- - F1: 0.9416
48
- - Accuracy: 0.9860
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
- | 0.0879 | 1.0 | 1756 | 0.0648 | 0.9103 | 0.9362 | 0.9231 | 0.9822 |
80
- | 0.0407 | 2.0 | 3512 | 0.0604 | 0.9267 | 0.9490 | 0.9377 | 0.9855 |
81
- | 0.0199 | 3.0 | 5268 | 0.0611 | 0.9332 | 0.9502 | 0.9416 | 0.9860 |
82
 
83
 
84
  ### Framework versions
85
 
86
- - Transformers 4.20.0
87
  - Pytorch 1.11.0+cu113
88
  - Datasets 2.3.2
89
  - Tokenizers 0.12.1
 
22
  metrics:
23
  - name: Precision
24
  type: precision
25
+ value: 0.9337299619897538
26
  - name: Recall
27
  type: recall
28
+ value: 0.9508582968697409
29
  - name: F1
30
  type: f1
31
+ value: 0.9422162928374885
32
  - name: Accuracy
33
  type: accuracy
34
+ value: 0.9861217401542356
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: 0.0637
45
+ - Precision: 0.9337
46
+ - Recall: 0.9509
47
+ - F1: 0.9422
48
+ - Accuracy: 0.9861
49
 
50
  ## Model description
51
 
 
76
 
77
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
78
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
79
+ | 0.0867 | 1.0 | 1756 | 0.0633 | 0.9132 | 0.9369 | 0.9249 | 0.9831 |
80
+ | 0.039 | 2.0 | 3512 | 0.0599 | 0.9333 | 0.9495 | 0.9414 | 0.9862 |
81
+ | 0.0202 | 3.0 | 5268 | 0.0637 | 0.9337 | 0.9509 | 0.9422 | 0.9861 |
82
 
83
 
84
  ### Framework versions
85
 
86
+ - Transformers 4.20.1
87
  - Pytorch 1.11.0+cu113
88
  - Datasets 2.3.2
89
  - Tokenizers 0.12.1