End of training

README.md

@@ -9,60 +9,29 @@ metrics:
 model-index:
 - name: vulnerability-severity-classification-roberta-base
   results: []
-datasets:
-- CIRCL/vulnerability-scores
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# VLAI: A RoBERTa-Based Model for Automated Vulnerability Severity Classification
-
-# Severity classification
-
-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).
-
-The model was presented in the paper [VLAI: A RoBERTa-Based Model for Automated Vulnerability Severity Classification](https://huggingface.co/papers/2507.03607).
-
-**Abstract:** VLAI is a transformer-based model that predicts software vulnerability severity levels directly from text descriptions. Built on RoBERTa, VLAI is fine-tuned on over 600,000 real-world vulnerabilities and achieves over 82% accuracy in predicting severity categories, enabling faster and more consistent triage ahead of manual CVSS scoring. The model and dataset are open-source and integrated into the Vulnerability-Lookup service.
-
-You can read [this page](https://www.vulnerability-lookup.org/user-manual/ai/) for more information.
-
-This model is cited in arxiv.org/abs/2507.03607.
+# vulnerability-severity-classification-roberta-base
 
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5084
+- Accuracy: 0.8277
 
 ## Model description
 
-It is a classification model and is aimed to assist in classifying vulnerabilities by severity based on their descriptions.
-
-
-## How to get started with the model
-
-```python
-from transformers import AutoModelForSequenceClassification, AutoTokenizer
-import torch
-
-labels = ["low", "medium", "high", "critical"]
+More information needed
 
-model_name = "CIRCL/vulnerability-severity-classification-distilbert-base-uncased"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForSequenceClassification.from_pretrained(model_name)
-model.eval()
+## Intended uses & limitations
 
-test_description = "SAP NetWeaver Visual Composer Metadata Uploader is not protected with a proper authorization, allowing unauthenticated agent to upload potentially malicious executable binaries \
-that could severely harm the host system. This could significantly affect the confidentiality, integrity, and availability of the targeted system."
-inputs = tokenizer(test_description, return_tensors="pt", truncation=True, padding=True)
+More information needed
 
-# Run inference
-with torch.no_grad():
-    outputs = model(**inputs)
-    predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+## Training and evaluation data
 
-# Print results
-print("Predictions:", predictions)
-predicted_class = torch.argmax(predictions, dim=-1).item()
-print("Predicted severity:", labels[predicted_class])
-```
+More information needed
 
 ## Training procedure
 
@@ -81,11 +50,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step   | Validation Loss | Accuracy |
 |:-------------:|:-----:|:------:|:---------------:|:--------:|
-| 0.603         | 1.0   | 27953  | 0.6582          | 0.7378   |
-| 0.6564        | 2.0   | 55906  | 0.5723          | 0.7726   |
-| 0.4861        | 3.0   | 83859  | 0.5290          | 0.7975   |
-| 0.4009        | 4.0   | 111812 | 0.5012          | 0.8156   |
-| 0.3478        | 5.0   | 139765 | 0.5005          | 0.8282   |
+| 0.5976        | 1.0   | 27995  | 0.6547          | 0.7422   |
+| 0.4254        | 2.0   | 55990  | 0.5822          | 0.7759   |
+| 0.5858        | 3.0   | 83985  | 0.5263          | 0.7982   |
+| 0.4801        | 4.0   | 111980 | 0.5008          | 0.8184   |
+| 0.3388        | 5.0   | 139975 | 0.5084          | 0.8277   |
 
 
 ### Framework versions
@@ -93,4 +62,4 @@ The following hyperparameters were used during training:
 - Transformers 4.51.3
 - Pytorch 2.7.1+cu126
 - Datasets 3.6.0
-- Tokenizers 0.21.1
+- Tokenizers 0.21.1

emissions.csv

@@ -1,2 +1,2 @@
 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
-2025-07-12T00:16:13,codecarbon,55180375-7bba-4fbc-bdc7-e323bc521848,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,33262.71693833545,0.6005853656266635,1.8055812059491925e-05,42.5,373.5268909024996,94.34468364715576,0.3924591785186284,4.441933271877076,0.8711770814119051,5.705569531807601,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
+2025-07-16T18:02:09,codecarbon,3f10a17e-3bd2-450f-96e0-0578c31ff090,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,33548.023177720606,0.6049317711968585,1.8031815704676047e-05,42.5,407.60668468427133,94.34468364715576,0.3958289673632734,4.472373492618146,0.878657986679406,5.746860446660825,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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b5c02f294fa03a2dd2006639c8784fbfbef95eea7782b8255586acccc9351b
+oid sha256:423157749697f9a570feec8e51fdd15d7174e928234a322897ab94a0f3ce7fe2
 size 498618976