Hugging Face's logo

ViktorDo
/
BioBERT-finetuned-ner-conll2003

Token Classification
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
2
ViktorDo commited on
Commit
46d89dd
·
1 Parent(s): 48f4b30

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -12
README.md CHANGED
@@ -23,16 +23,16 @@ model-index:
23
  metrics:
24
  - name: Precision
25
  type: precision
26
- value: 0.8195537004334564
27
  - name: Recall
28
  type: recall
29
- value: 0.8591383372601817
30
  - name: F1
31
  type: f1
32
- value: 0.8388793032618519
33
  - name: Accuracy
34
  type: accuracy
35
- value: 0.9667691125624279
36
  ---
37
 
38
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -42,11 +42,11 @@ should probably proofread and complete it, then remove this comment. -->
42
 
43
  This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) on the conll2003 dataset.
44
  It achieves the following results on the evaluation set:
45
- - Loss: 0.1099
46
- - Precision: 0.8196
47
- - Recall: 0.8591
48
- - F1: 0.8389
49
- - Accuracy: 0.9668
50
 
51
  ## Model description
52
 
@@ -71,18 +71,20 @@ The following hyperparameters were used during training:
71
  - seed: 42
72
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
  - lr_scheduler_type: linear
74
- - num_epochs: 1
75
 
76
  ### Training results
77
 
78
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
79
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
80
- | 0.1335 | 1.0 | 1756 | 0.1099 | 0.8196 | 0.8591 | 0.8389 | 0.9668 |
 
 
81
 
82
 
83
  ### Framework versions
84
 
85
  - Transformers 4.29.2
86
- - Pytorch 2.0.0+cu118
87
  - Datasets 2.12.0
88
  - Tokenizers 0.13.3
 
23
  metrics:
24
  - name: Precision
25
  type: precision
26
+ value: 0.8879153579103984
27
  - name: Recall
28
  type: recall
29
+ value: 0.9039044092898014
30
  - name: F1
31
  type: f1
32
+ value: 0.8958385455758486
33
  - name: Accuracy
34
  type: accuracy
35
+ value: 0.9764282970199221
36
  ---
37
 
38
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
42
 
43
  This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) on the conll2003 dataset.
44
  It achieves the following results on the evaluation set:
45
+ - Loss: 0.1057
46
+ - Precision: 0.8879
47
+ - Recall: 0.9039
48
+ - F1: 0.8958
49
+ - Accuracy: 0.9764
50
 
51
  ## Model description
52
 
 
71
  - seed: 42
72
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
73
  - lr_scheduler_type: linear
74
+ - num_epochs: 3
75
 
76
  ### Training results
77
 
78
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
79
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
80
+ | 0.133 | 1.0 | 1756 | 0.1027 | 0.8459 | 0.8672 | 0.8564 | 0.9699 |
81
+ | 0.0585 | 2.0 | 3512 | 0.0992 | 0.8785 | 0.8995 | 0.8889 | 0.9749 |
82
+ | 0.0299 | 3.0 | 5268 | 0.1057 | 0.8879 | 0.9039 | 0.8958 | 0.9764 |
83
 
84
 
85
  ### Framework versions
86
 
87
  - Transformers 4.29.2
88
+ - Pytorch 2.0.1+cu118
89
  - Datasets 2.12.0
90
  - Tokenizers 0.13.3