Hugging Face's logo

Brizape
/
SETH_29_03

Token Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
Brizape commited on
Commit
f6b1c0a
•
1 Parent(s): 1f3c3e6

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -20
README.md CHANGED
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.0728
23
- - Precision: 0.6968
24
- - Recall: 0.8623
25
- - F1: 0.7708
26
- - Accuracy: 0.9812
27
 
28
  ## Model description
29
 
@@ -42,7 +42,7 @@ More information needed
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
- - learning_rate: 2e-05
46
  - train_batch_size: 16
47
  - eval_batch_size: 16
48
  - seed: 42
@@ -54,20 +54,19 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
- | 0.566 | 0.96 | 25 | 0.2133 | 0.0 | 0.0 | 0.0 | 0.9583 |
58
- | 0.1302 | 1.92 | 50 | 0.0929 | 0.6059 | 0.6351 | 0.6202 | 0.9664 |
59
- | 0.0737 | 2.88 | 75 | 0.0747 | 0.5749 | 0.8124 | 0.6733 | 0.9739 |
60
- | 0.0575 | 3.85 | 100 | 0.0677 | 0.6085 | 0.7866 | 0.6862 | 0.9770 |
61
- | 0.0542 | 4.81 | 125 | 0.0650 | 0.6371 | 0.8640 | 0.7334 | 0.9774 |
62
- | 0.0382 | 5.77 | 150 | 0.0591 | 0.6991 | 0.8158 | 0.7530 | 0.9808 |
63
- | 0.0371 | 6.73 | 175 | 0.0584 | 0.6937 | 0.8382 | 0.7592 | 0.9810 |
64
- | 0.0299 | 7.69 | 200 | 0.0593 | 0.6968 | 0.8348 | 0.7596 | 0.9806 |
65
- | 0.0279 | 8.65 | 225 | 0.0617 | 0.7101 | 0.8348 | 0.7674 | 0.9818 |
66
- | 0.0249 | 9.62 | 250 | 0.0641 | 0.7262 | 0.7762 | 0.7504 | 0.9809 |
67
- | 0.0205 | 10.58 | 275 | 0.0655 | 0.7284 | 0.8399 | 0.7802 | 0.9831 |
68
- | 0.021 | 11.54 | 300 | 0.0659 | 0.7011 | 0.8399 | 0.7643 | 0.9811 |
69
- | 0.0173 | 12.5 | 325 | 0.0659 | 0.7271 | 0.8210 | 0.7712 | 0.9824 |
70
- | 0.0149 | 13.46 | 350 | 0.0728 | 0.6968 | 0.8623 | 0.7708 | 0.9812 |
71
 
72
 
73
  ### Framework versions
 
19
 
20
  This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.0866
23
+ - Precision: 0.7204
24
+ - Recall: 0.8468
25
+ - F1: 0.7785
26
+ - Accuracy: 0.9819
27
 
28
  ## Model description
29
 
 
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
+ - learning_rate: 5e-05
46
  - train_batch_size: 16
47
  - eval_batch_size: 16
48
  - seed: 42
 
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
56
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
57
+ | 0.3731 | 0.96 | 25 | 0.1863 | 0.0 | 0.0 | 0.0 | 0.9583 |
58
+ | 0.1139 | 1.92 | 50 | 0.0862 | 0.4524 | 0.6540 | 0.5348 | 0.9664 |
59
+ | 0.0654 | 2.88 | 75 | 0.0737 | 0.5914 | 0.8244 | 0.6887 | 0.9739 |
60
+ | 0.051 | 3.85 | 100 | 0.0646 | 0.6340 | 0.8227 | 0.7161 | 0.9789 |
61
+ | 0.0444 | 4.81 | 125 | 0.0769 | 0.5938 | 0.8554 | 0.7010 | 0.9732 |
62
+ | 0.031 | 5.77 | 150 | 0.0660 | 0.6541 | 0.8692 | 0.7465 | 0.9784 |
63
+ | 0.026 | 6.73 | 175 | 0.0641 | 0.7186 | 0.8262 | 0.7686 | 0.9814 |
64
+ | 0.0217 | 7.69 | 200 | 0.0682 | 0.6985 | 0.8571 | 0.7697 | 0.9813 |
65
+ | 0.0167 | 8.65 | 225 | 0.0678 | 0.7246 | 0.7969 | 0.7590 | 0.9809 |
66
+ | 0.0129 | 9.62 | 250 | 0.0727 | 0.7488 | 0.7900 | 0.7688 | 0.9825 |
67
+ | 0.0107 | 10.58 | 275 | 0.0778 | 0.7242 | 0.8451 | 0.7800 | 0.9818 |
68
+ | 0.0085 | 11.54 | 300 | 0.0784 | 0.7188 | 0.8537 | 0.7805 | 0.9820 |
69
+ | 0.0064 | 12.5 | 325 | 0.0866 | 0.7204 | 0.8468 | 0.7785 | 0.9819 |
 
70
 
71
 
72
  ### Framework versions