End of training

README.md

@@ -9,56 +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.
+# 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: 0.4997
+- Accuracy: 0.8276
 
 ## Model description
 
-It is a classification model and is aimed to assist in classifying vulnerabilities by severity based on their descriptions.
+More information needed
 
-## How to get started with the model
+## Intended uses & limitations
 
-```python
-from transformers import AutoModelForSequenceClassification, AutoTokenizer
-import torch
+More information needed
 
-labels = ["low", "medium", "high", "critical"]
-
-model_name = "CIRCL/vulnerability-severity-classification-roberta-base"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForSequenceClassification.from_pretrained(model_name)
-model.eval()
-
-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)
-
-# 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])
-```
+## Training and evaluation data
 
+More information needed
 
 ## Training procedure
 
@@ -73,19 +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: 0.5071
-- Accuracy: 0.8242
-
 ### Training results
 
 | Training Loss | Epoch | Step   | Validation Loss | Accuracy |
 |:-------------:|:-----:|:------:|:---------------:|:--------:|
-| 0.578         | 1.0   | 29087  | 0.6267          | 0.7451   |
-| 0.479         | 2.0   | 58174  | 0.5954          | 0.7728   |
-| 0.5272        | 3.0   | 87261  | 0.5361          | 0.7954   |
-| 0.5081        | 4.0   | 116348 | 0.5057          | 0.8155   |
-| 0.2614        | 5.0   | 145435 | 0.5071          | 0.8242   |
+| 0.75          | 1.0   | 29142  | 0.6350          | 0.7399   |
+| 0.4925        | 2.0   | 58284  | 0.5660          | 0.7726   |
+| 0.5897        | 3.0   | 87426  | 0.5228          | 0.7979   |
+| 0.3958        | 4.0   | 116568 | 0.5046          | 0.8176   |
+| 0.3136        | 5.0   | 145710 | 0.4997          | 0.8276   |
 
 
 ### 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
-2025-09-30T12:25:21,codecarbon,4f6ae632-1482-40c9-8a41-517ca5876644,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,22857.829803195316,0.41428815681587067,1.812456214710099e-05,42.5,324.04679076926755,94.34468507766725,0.26967573376890325,3.067447771178479,0.5986198884184825,3.935743393365861,Luxembourg,LUX,luxembourg,,,Linux-6.8.0-71-generic-x86_64-with-glibc2.39,3.12.3,2.8.4,64,AMD EPYC 9124 16-Core Processor,2,2 x NVIDIA L40S,6.1294,49.6113,251.5858268737793,machine,N,1.0
+2025-10-06T15:51:23,codecarbon,3e10db32-e6ba-4e56-904b-993909f742f3,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,22786.653630222194,0.41209494913485034,1.8084926195054996e-05,42.5,345.5288142486328,94.34468507766725,0.26884445088668063,3.0492884038731916,0.5967750343830369,3.9149078891429117,Luxembourg,LUX,luxembourg,,,Linux-6.8.0-71-generic-x86_64-with-glibc2.39,3.12.3,2.8.4,64,AMD EPYC 9124 16-Core Processor,2,2 x NVIDIA L40S,6.1294,49.6113,251.5858268737793,machine,N,1.0