End of training

README.md

@@ -9,62 +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) [[arXiv](https://arxiv.org/abs/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.
-
-
-## Model description
-
-It is a classification model and is aimed to assist in classifying vulnerabilities by severity based on their descriptions.
+# 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: 0.5098
-- Accuracy: 0.8258
+- Loss: 0.5065
+- Accuracy: 0.8293
 
-## How to get started with the model
-
-```python
-from transformers import AutoModelForSequenceClassification, AutoTokenizer
-import torch
-
-labels = ["low", "medium", "high", "critical"]
+## Model description
 
-model_name = "CIRCL/vulnerability-severity-classification-roberta-base"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForSequenceClassification.from_pretrained(model_name)
-model.eval()
+More information needed
 
-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)
+## Intended uses & limitations
 
-# Run inference
-with torch.no_grad():
-    outputs = model(**inputs)
-    predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
+More information needed
 
-# Print results
-print("Predictions:", predictions)
-predicted_class = torch.argmax(predictions, dim=-1).item()
-print("Predicted severity:", labels[predicted_class])
-```
+## Training and evaluation data
 
+More information needed
 
 ## Training procedure
 
@@ -83,11 +50,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step   | Validation Loss | Accuracy |
 |:-------------:|:-----:|:------:|:---------------:|:--------:|
-| 0.6421        | 1.0   | 28117  | 0.6400          | 0.7436   |
-| 0.5734        | 2.0   | 56234  | 0.5903          | 0.7758   |
-| 0.4304        | 3.0   | 84351  | 0.5422          | 0.7951   |
-| 0.4694        | 4.0   | 112468 | 0.5055          | 0.8176   |
-| 0.3141        | 5.0   | 140585 | 0.5098          | 0.8258   |
+| 0.5365        | 1.0   | 28319  | 0.6723          | 0.7432   |
+| 0.4935        | 2.0   | 56638  | 0.5961          | 0.7707   |
+| 0.4246        | 3.0   | 84957  | 0.5398          | 0.7981   |
+| 0.4927        | 4.0   | 113276 | 0.5052          | 0.8193   |
+| 0.2864        | 5.0   | 141595 | 0.5065          | 0.8293   |
 
 
 ### Framework versions

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
-2025-07-25T15:09:30,codecarbon,1671c5cf-d51d-4aad-994c-a149fd2d189e,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,33557.31429638248,0.6052922027774613,1.803756395495311e-05,42.5,433.1611236849119,94.34468364715576,0.39593592552908535,4.47545033341288,0.8788982928707405,5.75028455181271,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
+2025-08-12T14:50:28,codecarbon,8d66914a-9b1d-4e8d-b5b0-197aae7695b1,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,33622.2954240907,0.6071869809020806,1.8059057932940093e-05,42.5,391.41603724835056,94.34468364715576,0.396695449095465,4.49100706696936,0.8805824549323915,5.768284970997222,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 sha256:13cce5d6521fabf3040c11601ecac76db205225f04f4ed549987b5a388faa0ad
+oid sha256:1c24282b65ebd19bde58f9c83ce25596e566ff521d043484c1095d62dbbe1977
 size 498618976