Hugging Face's logo

filippo-baglini
/
biobert_finetuned_ncbi_disease

Token Classification
Transformers
Safetensors
bert
Generated from Trainer
Eval Results
Model card Files
xet
Community
filippo-baglini commited on
Commit
c084fb3
·
verified ·
1 Parent(s): 86bf391

Training finished

Browse files
Files changed (2) hide show
  1. README.md +13 -16
  2. model.safetensors +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: F1
24
  type: f1
25
- value: 0.8246674727932287
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.1](https://huggingface.co/dmis-lab/biobert-base-cased-v1.1) on the ncbi_disease dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.0878
36
- - F1: 0.8247
37
 
38
  ## Model description
39
 
@@ -64,19 +64,16 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | F1 |
66
  |:-------------:|:-----:|:----:|:---------------:|:------:|
67
- | 1.0424 | 1.0 | 170 | 0.8040 | 0.0173 |
68
- | 0.5079 | 2.0 | 340 | 0.2580 | 0.0434 |
69
- | 0.2083 | 3.0 | 510 | 0.1332 | 0.5373 |
70
- | 0.1339 | 4.0 | 680 | 0.0979 | 0.6069 |
71
- | 0.0935 | 5.0 | 850 | 0.0805 | 0.6558 |
72
- | 0.0686 | 6.0 | 1020 | 0.0741 | 0.7209 |
73
- | 0.0529 | 7.0 | 1190 | 0.0698 | 0.7827 |
74
- | 0.0412 | 8.0 | 1360 | 0.0684 | 0.8048 |
75
- | 0.0311 | 9.0 | 1530 | 0.0764 | 0.8179 |
76
- | 0.0243 | 10.0 | 1700 | 0.0796 | 0.8149 |
77
- | 0.0185 | 11.0 | 1870 | 0.0794 | 0.8230 |
78
- | 0.0155 | 12.0 | 2040 | 0.0846 | 0.8190 |
79
- | 0.012 | 13.0 | 2210 | 0.0878 | 0.8247 |
80
 
81
 
82
  ### Framework versions
 
22
  metrics:
23
  - name: F1
24
  type: f1
25
+ value: 0.8341404358353511
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.1](https://huggingface.co/dmis-lab/biobert-base-cased-v1.1) on the ncbi_disease dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.0925
36
+ - F1: 0.8341
37
 
38
  ## Model description
39
 
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | F1 |
66
  |:-------------:|:-----:|:----:|:---------------:|:------:|
67
+ | 0.8751 | 1.0 | 170 | 0.4697 | 0.0 |
68
+ | 0.291 | 2.0 | 340 | 0.1498 | 0.4705 |
69
+ | 0.1379 | 3.0 | 510 | 0.0959 | 0.6176 |
70
+ | 0.0841 | 4.0 | 680 | 0.0791 | 0.7278 |
71
+ | 0.058 | 5.0 | 850 | 0.0738 | 0.7739 |
72
+ | 0.042 | 6.0 | 1020 | 0.0738 | 0.7872 |
73
+ | 0.0307 | 7.0 | 1190 | 0.0742 | 0.8215 |
74
+ | 0.0215 | 8.0 | 1360 | 0.0776 | 0.8103 |
75
+ | 0.0152 | 9.0 | 1530 | 0.0886 | 0.8228 |
76
+ | 0.011 | 10.0 | 1700 | 0.0925 | 0.8341 |
 
 
 
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90d1d1d66bbd7f4f3f1434bda5fa0cfdb108cb446a8dd08cf6cf3af0ceb72eab
3
  size 430911284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89d2d8eb415f384e28438cfabbc9691ba025e79b8443cd55cdf97e77f2e49036
3
  size 430911284