End of training

README.md

@@ -1,67 +1,37 @@
 ---
 library_name: transformers
-license: cc-by-4.0
+license: mit
 base_model: roberta-base
-metrics:
-- accuracy
 tags:
 - generated_from_trainer
-- text-classification
-- classification
-- nlp
-- vulnerability
+metrics:
+- accuracy
 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.
+# 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: 0.4942
+- Accuracy: 0.8233
 
 ## 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
+More information needed
 
-labels = ["low", "medium", "high", "critical"]
+## Intended uses & limitations
 
-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)
+## Training and evaluation data
 
-# Run inference
-with torch.no_grad():
-    outputs = model(**inputs)
-    predictions = torch.nn.functional.softmax(outputs.logits, dim=-1)
-
-# Print results
-print("Predictions:", predictions)
-predicted_class = torch.argmax(predictions, dim=-1).item()
-print("Predicted severity:", labels[predicted_class])
-```
+More information needed
 
 ## Training procedure
 
@@ -76,19 +46,15 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 5
 
-It achieves the following results on the evaluation set:
-- Loss: 0.5034
-- Accuracy: 0.8235
-
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.5734        | 1.0   | 15069 | 0.6289          | 0.7407   |
-| 0.5761        | 2.0   | 30138 | 0.5726          | 0.7711   |
-| 0.5469        | 3.0   | 45207 | 0.5310          | 0.7939   |
-| 0.3891        | 4.0   | 60276 | 0.4990          | 0.8140   |
-| 0.4005        | 5.0   | 75345 | 0.5034          | 0.8235   |
+| 0.7037        | 1.0   | 15125 | 0.6343          | 0.7375   |
+| 0.54          | 2.0   | 30250 | 0.5637          | 0.7730   |
+| 0.4651        | 3.0   | 45375 | 0.5438          | 0.7928   |
+| 0.4133        | 4.0   | 60500 | 0.5025          | 0.8131   |
+| 0.3927        | 5.0   | 75625 | 0.4942          | 0.8233   |
 
 
 ### 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,water_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,cpu_utilization_percent,gpu_utilization_percent,ram_utilization_percent,ram_used_gb,on_cloud,pue,wue
-2026-01-13T16:42:44,codecarbon,239a5323-08fa-42df-83c8-2497690fa6f1,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,14451.823297226976,0.5437364522873581,3.762407283181289e-05,364.9353051226869,853.6184090848112,70.0,1.4633795076748908,3.42174342378144,0.2803811135296457,5.165504044985969,0.0,Luxembourg,LUX,,,,Linux-6.8.0-90-generic-x86_64-with-glibc2.39,3.12.3,3.2.1,224,Intel(R) Xeon(R) Platinum 8480+,4,4 x NVIDIA L40S,6.1661,49.7498,2015.3354835510254,machine,0.6606100611450806,72.29269733185103,1.0025222345747637,20.782332318567317,N,1.0,0.0
+2026-01-19T10:49:01,codecarbon,e47f1fc5-7153-4bef-b60f-6ecee5cfea74,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,14269.086253645946,0.5400655046401097,3.7848639712449396e-05,364.51917863207274,862.2434481668117,70.0,1.443068396622125,3.410740521090237,0.2768210723136751,5.130629990026026,0.0,Luxembourg,LUX,,,,Linux-6.8.0-90-generic-x86_64-with-glibc2.39,3.12.3,3.2.1,224,Intel(R) Xeon(R) Platinum 8480+,4,4 x NVIDIA L40S,6.1661,49.7498,2015.3354835510254,machine,0.6738405236117954,73.27106059539729,1.0799985924414104,21.291425154725776,N,1.0,0.0