Hugging Face's logo

CIRCL
/
vulnerability-severity-classification-roberta-base

Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
classification
nlp
vulnerability
text-embeddings-inference
Model card Files
xet
 Community
1
cedricbonhomme commited on
Commit
4492677
·
verified ·
1 Parent(s): da2009d

End of training

Browse files
Files changed (2) hide show
  1. README.md +20 -20
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,21 +18,21 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 2.0603
22
- - Accuracy: 0.8169
23
- - F1 Macro: 0.7447
24
- - Low Precision: 0.6569
25
- - Low Recall: 0.4883
26
- - Low F1: 0.5602
27
- - Medium Precision: 0.8417
28
- - Medium Recall: 0.8775
29
- - Medium F1: 0.8592
30
- - High Precision: 0.8177
31
- - High Recall: 0.8029
32
- - High F1: 0.8102
33
- - Critical Precision: 0.7563
34
- - Critical Recall: 0.7421
35
- - Critical F1: 0.7491
36
 
37
  ## Model description
38
 
@@ -63,11 +63,11 @@ The following hyperparameters were used during training:
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Low Precision | Low Recall | Low F1 | Medium Precision | Medium Recall | Medium F1 | High Precision | High Recall | High F1 | Critical Precision | Critical Recall | Critical F1 |
65
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:-------------:|:----------:|:------:|:----------------:|:-------------:|:---------:|:--------------:|:-----------:|:-------:|:------------------:|:---------------:|:-----------:|
66
- | 2.7685 | 1.0 | 16320 | 2.5328 | 0.7375 | 0.6375 | 0.6275 | 0.2956 | 0.4019 | 0.7555 | 0.8595 | 0.8041 | 0.7563 | 0.6668 | 0.7087 | 0.6296 | 0.6410 | 0.6352 |
67
- | 2.1832 | 2.0 | 32640 | 2.3441 | 0.7670 | 0.6710 | 0.6478 | 0.3370 | 0.4434 | 0.8049 | 0.8441 | 0.8240 | 0.7431 | 0.7665 | 0.7546 | 0.7050 | 0.6237 | 0.6618 |
68
- | 2.0311 | 3.0 | 48960 | 2.1676 | 0.7900 | 0.7086 | 0.6366 | 0.4174 | 0.5042 | 0.8369 | 0.8434 | 0.8402 | 0.7701 | 0.7915 | 0.7806 | 0.7079 | 0.7112 | 0.7096 |
69
- | 1.5652 | 4.0 | 65280 | 2.0563 | 0.8083 | 0.7323 | 0.6671 | 0.4477 | 0.5358 | 0.8450 | 0.8597 | 0.8523 | 0.7981 | 0.8052 | 0.8016 | 0.7321 | 0.7467 | 0.7394 |
70
- | 1.4185 | 5.0 | 81600 | 2.0603 | 0.8169 | 0.7447 | 0.6569 | 0.4883 | 0.5602 | 0.8417 | 0.8775 | 0.8592 | 0.8177 | 0.8029 | 0.8102 | 0.7563 | 0.7421 | 0.7491 |
71
 
72
 
73
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 2.0549
22
+ - Accuracy: 0.8168
23
+ - F1 Macro: 0.7486
24
+ - Low Precision: 0.6931
25
+ - Low Recall: 0.4992
26
+ - Low F1: 0.5804
27
+ - Medium Precision: 0.8449
28
+ - Medium Recall: 0.8722
29
+ - Medium F1: 0.8584
30
+ - High Precision: 0.8083
31
+ - High Recall: 0.8124
32
+ - High F1: 0.8103
33
+ - Critical Precision: 0.7617
34
+ - Critical Recall: 0.7299
35
+ - Critical F1: 0.7455
36
 
37
  ## Model description
38
 
 
63
 
64
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Low Precision | Low Recall | Low F1 | Medium Precision | Medium Recall | Medium F1 | High Precision | High Recall | High F1 | Critical Precision | Critical Recall | Critical F1 |
65
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:-------------:|:----------:|:------:|:----------------:|:-------------:|:---------:|:--------------:|:-----------:|:-------:|:------------------:|:---------------:|:-----------:|
66
+ | 2.4224 | 1.0 | 16352 | 2.5629 | 0.7378 | 0.6209 | 0.7021 | 0.2288 | 0.3451 | 0.7902 | 0.8129 | 0.8014 | 0.7011 | 0.7546 | 0.7269 | 0.6479 | 0.5765 | 0.6101 |
67
+ | 2.1704 | 2.0 | 32704 | 2.3004 | 0.7693 | 0.6756 | 0.6116 | 0.3487 | 0.4442 | 0.8013 | 0.8491 | 0.8245 | 0.7664 | 0.7493 | 0.7577 | 0.6794 | 0.6727 | 0.6760 |
68
+ | 2.1241 | 3.0 | 49056 | 2.1680 | 0.7906 | 0.7040 | 0.7357 | 0.3666 | 0.4894 | 0.8024 | 0.8852 | 0.8417 | 0.8044 | 0.7481 | 0.7752 | 0.7111 | 0.7082 | 0.7097 |
69
+ | 1.5991 | 4.0 | 65408 | 2.0822 | 0.8083 | 0.7326 | 0.7214 | 0.4372 | 0.5444 | 0.8378 | 0.8689 | 0.8531 | 0.8028 | 0.7983 | 0.8005 | 0.7279 | 0.7370 | 0.7324 |
70
+ | 1.6372 | 5.0 | 81760 | 2.0549 | 0.8168 | 0.7486 | 0.6931 | 0.4992 | 0.5804 | 0.8449 | 0.8722 | 0.8584 | 0.8083 | 0.8124 | 0.8103 | 0.7617 | 0.7299 | 0.7455 |
71
 
72
 
73
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b829d16fe281497ed5f9c56a4b3030886da609289a74209d5304f592330666c
3
  size 498618976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a02fca88e4cc69505091129c6eacd435a26eedafe6a4d35755ba9c3ddc692600
3
  size 498618976