cedricbonhomme commited on
Commit
c9bfc4f
·
verified ·
1 Parent(s): 1afc710

End of training

Browse files
Files changed (2) hide show
  1. README.md +14 -40
  2. emissions.csv +1 -1
README.md CHANGED
@@ -9,8 +9,6 @@ metrics:
9
  model-index:
10
  - name: vulnerability-severity-classification-roberta-base
11
  results: []
12
- datasets:
13
- - CIRCL/vulnerability-scores
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -18,46 +16,22 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # vulnerability-severity-classification-roberta-base
20
 
21
- This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the dataset [CIRCL/vulnerability-scores](https://huggingface.co/datasets/CIRCL/vulnerability-scores).
22
-
23
- You can read [this page](https://www.vulnerability-lookup.org/user-manual/ai/) for more information.
24
-
25
  It achieves the following results on the evaluation set:
26
- - Loss: 0.4877
27
- - Accuracy: 0.8327
28
 
29
  ## Model description
30
 
31
- It is a classification model and is aimed to assist in classifying vulnerabilities by severity based on their descriptions.
32
-
33
-
34
- ## How to get started with the model
35
-
36
- ```python
37
- from transformers import AutoModelForSequenceClassification, AutoTokenizer
38
- import torch
39
-
40
- labels = ["low", "medium", "high", "critical"]
41
 
42
- model_name = "CIRCL/vulnerability-severity-classification-distilbert-base-uncased"
43
- tokenizer = AutoTokenizer.from_pretrained(model_name)
44
- model = AutoModelForSequenceClassification.from_pretrained(model_name)
45
- model.eval()
46
 
47
- test_description = "SAP NetWeaver Visual Composer Metadata Uploader is not protected with a proper authorization, allowing unauthenticated agent to upload potentially malicious executable binaries \
48
- that could severely harm the host system. This could significantly affect the confidentiality, integrity, and availability of the targeted system."
49
- inputs = tokenizer(test_description, return_tensors="pt", truncation=True, padding=True)
50
 
51
- # Run inference
52
- with torch.no_grad():
53
- outputs = model(**inputs)
54
- predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
55
 
56
- # Print results
57
- print("Predictions:", predictions)
58
- predicted_class = torch.argmax(predictions, dim=-1).item()
59
- print("Predicted severity:", labels[predicted_class])
60
- ```
61
 
62
  ## Training procedure
63
 
@@ -76,11 +50,11 @@ The following hyperparameters were used during training:
76
 
77
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
78
  |:-------------:|:-----:|:------:|:---------------:|:--------:|
79
- | 0.6796 | 1.0 | 27610 | 0.6247 | 0.7486 |
80
- | 0.511 | 2.0 | 55220 | 0.5811 | 0.7754 |
81
- | 0.5079 | 3.0 | 82830 | 0.5179 | 0.8053 |
82
- | 0.3685 | 4.0 | 110440 | 0.4863 | 0.8231 |
83
- | 0.4885 | 5.0 | 138050 | 0.4877 | 0.8327 |
84
 
85
 
86
  ### Framework versions
@@ -88,4 +62,4 @@ The following hyperparameters were used during training:
88
  - Transformers 4.51.3
89
  - Pytorch 2.7.1+cu126
90
  - Datasets 3.6.0
91
- - Tokenizers 0.21.1
 
9
  model-index:
10
  - name: vulnerability-severity-classification-roberta-base
11
  results: []
 
 
12
  ---
13
 
14
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
16
 
17
  # vulnerability-severity-classification-roberta-base
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: 0.5027
22
+ - Accuracy: 0.8290
23
 
24
  ## Model description
25
 
26
+ More information needed
 
 
 
 
 
 
 
 
 
27
 
28
+ ## Intended uses & limitations
 
 
 
29
 
30
+ More information needed
 
 
31
 
32
+ ## Training and evaluation data
 
 
 
33
 
34
+ More information needed
 
 
 
 
35
 
36
  ## Training procedure
37
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
  |:-------------:|:-----:|:------:|:---------------:|:--------:|
53
+ | 0.6731 | 1.0 | 27750 | 0.6511 | 0.7357 |
54
+ | 0.6648 | 2.0 | 55500 | 0.5703 | 0.7746 |
55
+ | 0.427 | 3.0 | 83250 | 0.5215 | 0.8010 |
56
+ | 0.4361 | 4.0 | 111000 | 0.5099 | 0.8179 |
57
+ | 0.3167 | 5.0 | 138750 | 0.5027 | 0.8290 |
58
 
59
 
60
  ### Framework versions
 
62
  - Transformers 4.51.3
63
  - Pytorch 2.7.1+cu126
64
  - Datasets 3.6.0
65
+ - Tokenizers 0.21.1
emissions.csv CHANGED
@@ -1,2 +1,2 @@
1
  timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
2
- 2025-06-24T15:53:24,codecarbon,dea556a8-0fa6-48cd-83ec-f23d85db7c7c,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,32671.975663511083,0.590254076994602,1.806606625426124e-05,42.5,427.2816674683831,94.34468364715576,0.38548106524080844,4.366259382171364,0.8556816951697346,5.607422142581932,Luxembourg,LUX,luxembourg,,,Linux-6.8.0-60-generic-x86_64-with-glibc2.39,3.12.3,2.8.4,64,AMD EPYC 9124 16-Core Processor,2,2 x NVIDIA L40S,6.1294,49.6113,251.58582305908203,machine,N,1.0
 
1
  timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
2
+ 2025-06-30T21:37:53,codecarbon,fdd20567-9b6a-4e5e-b81a-d2f3561abea1,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,31939.66063390905,0.5761457661682887,1.803856881173678e-05,42.5,387.869585627133,94.34468364715576,0.37683512923984447,4.260060606934644,0.8364972525137364,5.473392988688225,Luxembourg,LUX,luxembourg,,,Linux-6.8.0-60-generic-x86_64-with-glibc2.39,3.12.3,2.8.4,64,AMD EPYC 9124 16-Core Processor,2,2 x NVIDIA L40S,6.1294,49.6113,251.58582305908203,machine,N,1.0