Hugging Face's logo

Santarabantoosoo
/
PathologyBERT-meningioma

Text Classification
Transformers
PyTorch
TensorBoard
bert
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
2
Santarabantoosoo commited on
Commit
cdd3c94
•
1 Parent(s): 88bd0b4

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -29
README.md CHANGED
@@ -18,13 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [tsantos/PathologyBERT](https://huggingface.co/tsantos/PathologyBERT) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.6939
22
- - Accuracy: 0.8696
23
- - Precision: 0.0
24
- - Recall: 0.0
25
- - F1: 0.0
26
- - Conf Matrix: [[ 0 12]
27
- [ 3 100]]
28
 
29
  ## Model description
30
 
@@ -53,28 +51,18 @@ The following hyperparameters were used during training:
53
 
54
  ### Training results
55
 
56
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Conf Matrix |
57
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:----------------------:|
58
- | 0.5537 | 1.0 | 71 | 0.5252 | 0.7304 | 0.0870 | 0.1667 | 0.1143 | [[ 2 10]
59
- [21 82]] |
60
- | 0.3702 | 2.0 | 142 | 0.3598 | 0.8870 | 0.0 | 0.0 | 0.0 | [[ 0 12]
61
- [ 1 102]] |
62
- | 0.2892 | 3.0 | 213 | 0.3999 | 0.8696 | 0.2 | 0.0833 | 0.1176 | [[ 1 11]
63
- [ 4 99]] |
64
- | 0.2745 | 4.0 | 284 | 0.4806 | 0.8870 | 0.0 | 0.0 | 0.0 | [[ 0 12]
65
- [ 1 102]] |
66
- | 0.2131 | 5.0 | 355 | 0.4988 | 0.8609 | 0.0 | 0.0 | 0.0 | [[ 0 12]
67
- [ 4 99]] |
68
- | 0.1685 | 6.0 | 426 | 0.6441 | 0.8348 | 0.1111 | 0.0833 | 0.0952 | [[ 1 11]
69
- [ 8 95]] |
70
- | 0.138 | 7.0 | 497 | 0.5988 | 0.8957 | 1.0 | 0.0 | 0.0 | [[ 0 12]
71
- [ 0 103]] |
72
- | 0.1069 | 8.0 | 568 | 0.6765 | 0.8609 | 0.0 | 0.0 | 0.0 | [[ 0 12]
73
- [ 4 99]] |
74
- | 0.1185 | 9.0 | 639 | 0.6838 | 0.8696 | 0.0 | 0.0 | 0.0 | [[ 0 12]
75
- [ 3 100]] |
76
- | 0.0891 | 10.0 | 710 | 0.6939 | 0.8696 | 0.0 | 0.0 | 0.0 | [[ 0 12]
77
- [ 3 100]] |
78
 
79
 
80
  ### Framework versions
18
 
19
  This model is a fine-tuned version of [tsantos/PathologyBERT](https://huggingface.co/tsantos/PathologyBERT) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.8123
22
+ - Accuracy: 0.8783
23
+ - Precision: 0.25
24
+ - Recall: 0.0833
25
+ - F1: 0.125
 
 
26
 
27
  ## Model description
28
 
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
55
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
56
+ | 0.3723 | 1.0 | 71 | 0.5377 | 0.7652 | 0.0588 | 0.0833 | 0.0690 |
57
+ | 0.3363 | 2.0 | 142 | 0.4191 | 0.8783 | 0.25 | 0.0833 | 0.125 |
58
+ | 0.2773 | 3.0 | 213 | 0.4701 | 0.8870 | 0.3333 | 0.0833 | 0.1333 |
59
+ | 0.2303 | 4.0 | 284 | 0.5831 | 0.8957 | 0.5 | 0.0833 | 0.1429 |
60
+ | 0.1657 | 5.0 | 355 | 0.7083 | 0.8348 | 0.1111 | 0.0833 | 0.0952 |
61
+ | 0.1228 | 6.0 | 426 | 1.0324 | 0.8 | 0.0769 | 0.0833 | 0.08 |
62
+ | 0.0967 | 7.0 | 497 | 0.8103 | 0.8696 | 0.2 | 0.0833 | 0.1176 |
63
+ | 0.0729 | 8.0 | 568 | 0.8711 | 0.8696 | 0.2 | 0.0833 | 0.1176 |
64
+ | 0.0624 | 9.0 | 639 | 0.7968 | 0.8783 | 0.25 | 0.0833 | 0.125 |
65
+ | 0.0534 | 10.0 | 710 | 0.8123 | 0.8783 | 0.25 | 0.0833 | 0.125 |
 
 
 
 
 
 
 
 
 
 
66
 
67
 
68
  ### Framework versions