Hugging Face's logo

GuCuChiara
/
NLP-HIBA_BiomedNLP-BiomedBERT-base-pretrained-model

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
GuCuChiara commited on
Commit
897ed4d
•
1 Parent(s): 4b244c4

Training complete

Browse files
Files changed (1) hide show
  1. README.md +18 -16
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.1766
24
- - Precision: 0.5977
25
- - Recall: 0.5730
26
- - F1: 0.5851
27
- - Accuracy: 0.9539
28
 
29
  ## Model description
30
 
@@ -49,22 +49,24 @@ The following hyperparameters were used during training:
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
- - num_epochs: 10
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
- | No log | 1.0 | 71 | 0.1981 | 0.2581 | 0.2239 | 0.2398 | 0.9266 |
59
- | No log | 2.0 | 142 | 0.1616 | 0.4514 | 0.3692 | 0.4062 | 0.9444 |
60
- | No log | 3.0 | 213 | 0.1514 | 0.5233 | 0.4727 | 0.4967 | 0.9482 |
61
- | No log | 4.0 | 284 | 0.1863 | 0.4522 | 0.5546 | 0.4982 | 0.9352 |
62
- | No log | 5.0 | 355 | 0.1582 | 0.5665 | 0.5245 | 0.5447 | 0.9498 |
63
- | No log | 6.0 | 426 | 0.1571 | 0.5915 | 0.5305 | 0.5593 | 0.9529 |
64
- | No log | 7.0 | 497 | 0.1652 | 0.5849 | 0.5586 | 0.5714 | 0.9527 |
65
- | 0.1311 | 8.0 | 568 | 0.1676 | 0.5858 | 0.5738 | 0.5798 | 0.9528 |
66
- | 0.1311 | 9.0 | 639 | 0.1748 | 0.5990 | 0.5562 | 0.5768 | 0.9537 |
67
- | 0.1311 | 10.0 | 710 | 0.1766 | 0.5977 | 0.5730 | 0.5851 | 0.9539 |
 
 
68
 
69
 
70
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext) on the None dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.2050
24
+ - Precision: 0.6079
25
+ - Recall: 0.5407
26
+ - F1: 0.5723
27
+ - Accuracy: 0.9528
28
 
29
  ## Model description
30
 
 
49
  - seed: 42
50
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
  - lr_scheduler_type: linear
52
+ - num_epochs: 12
53
 
54
  ### Training results
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | No log | 1.0 | 71 | 0.2223 | 0.3125 | 0.1619 | 0.2133 | 0.9212 |
59
+ | No log | 2.0 | 142 | 0.1599 | 0.5228 | 0.3539 | 0.4221 | 0.9446 |
60
+ | No log | 3.0 | 213 | 0.1472 | 0.5298 | 0.4385 | 0.4798 | 0.9470 |
61
+ | No log | 4.0 | 284 | 0.1441 | 0.5885 | 0.4729 | 0.5244 | 0.9514 |
62
+ | No log | 5.0 | 355 | 0.1675 | 0.5654 | 0.5146 | 0.5388 | 0.9491 |
63
+ | No log | 6.0 | 426 | 0.1592 | 0.5860 | 0.5082 | 0.5443 | 0.9521 |
64
+ | No log | 7.0 | 497 | 0.1634 | 0.5621 | 0.5587 | 0.5604 | 0.9509 |
65
+ | 0.1349 | 8.0 | 568 | 0.1897 | 0.5803 | 0.5182 | 0.5475 | 0.9515 |
66
+ | 0.1349 | 9.0 | 639 | 0.1880 | 0.5699 | 0.5539 | 0.5618 | 0.9506 |
67
+ | 0.1349 | 10.0 | 710 | 0.1939 | 0.5923 | 0.5415 | 0.5657 | 0.9525 |
68
+ | 0.1349 | 11.0 | 781 | 0.1988 | 0.5863 | 0.5475 | 0.5662 | 0.9518 |
69
+ | 0.1349 | 12.0 | 852 | 0.2050 | 0.6079 | 0.5407 | 0.5723 | 0.9528 |
70
 
71
 
72
  ### Framework versions