End of training

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: transformers
-license: cc-by-4.0
+license: mit
 base_model: roberta-base
 tags:
 - generated_from_trainer
@@ -9,55 +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
+# vulnerability-severity-classification-roberta-base
 
-# 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.
+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: 0.4988
+- Accuracy: 0.8239
 
 ## 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
+More information needed
 
-```python
-from transformers import AutoModelForSequenceClassification, AutoTokenizer
-import torch
+## Intended uses & limitations
 
-labels = ["low", "medium", "high", "critical"]
+More information needed
 
-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
 
@@ -72,20 +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: 0.5053
-- Accuracy: 0.8195
-  
-
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.6458        | 1.0   | 14962 | 0.6352          | 0.7394   |
-| 0.4643        | 2.0   | 29924 | 0.5741          | 0.7702   |
-| 0.5519        | 3.0   | 44886 | 0.5261          | 0.7922   |
-| 0.3822        | 4.0   | 59848 | 0.5054          | 0.8111   |
-| 0.344         | 5.0   | 74810 | 0.5053          | 0.8195   |
+| 0.5754        | 1.0   | 14998 | 0.6411          | 0.7426   |
+| 0.5831        | 2.0   | 29996 | 0.5794          | 0.7704   |
+| 0.4704        | 3.0   | 44994 | 0.5280          | 0.7950   |
+| 0.3535        | 4.0   | 59992 | 0.5139          | 0.8138   |
+| 0.3464        | 5.0   | 74990 | 0.4988          | 0.8239   |
 
 
 ### 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
-2025-12-27T02:30:50,codecarbon,053a0694-69e4-4f2a-b6b7-c48517c95402,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,13934.410282625999,0.6770843193932654,4.859081264726949e-05,42.5,598.0692513088488,755.7507977485657,0.16420767100260394,3.3485438799440677,2.919559131755385,6.432310682702044,Luxembourg,LUX,,,,Linux-6.8.0-90-generic-x86_64-with-glibc2.39,3.12.3,2.8.4,224,Intel(R) Xeon(R) Platinum 8480+,4,4 x NVIDIA L40S,6.1661,49.7498,2015.3354606628418,machine,N,1.0
+2026-01-02T13:33:24,codecarbon,6f8649af-63f5-4be4-be38-b3a5e984904d,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,14058.473727937904,0.6821544073612349,4.852265050690487e-05,42.5,627.1709501771732,755.7507977485657,0.16565008514747048,3.369631439036325,2.9451950664628326,6.480476590646617,Luxembourg,LUX,,,,Linux-6.8.0-90-generic-x86_64-with-glibc2.39,3.12.3,2.8.4,224,Intel(R) Xeon(R) Platinum 8480+,4,4 x NVIDIA L40S,6.1661,49.7498,2015.3354606628418,machine,N,1.0