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
@@ -9,56 +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: 0.5041
+- Accuracy: 0.8218
 
 ## 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
 
@@ -73,20 +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: 0.4988
-- Accuracy: 0.8239
-
-
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 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   |
+| 0.659         | 1.0   | 15051 | 0.6294          | 0.7367   |
+| 0.5518        | 2.0   | 30102 | 0.5712          | 0.7724   |
+| 0.466         | 3.0   | 45153 | 0.5371          | 0.7916   |
+| 0.4868        | 4.0   | 60204 | 0.5015          | 0.8125   |
+| 0.3534        | 5.0   | 75255 | 0.5041          | 0.8218   |
 
 
 ### 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
-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
+2026-01-09T12:38:40,codecarbon,370078c2-c4c4-4f0b-a15d-805a477a8e26,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,14062.196396406001,0.6835295413886745,4.860759458340165e-05,42.5,364.8842991796195,755.7508063316345,0.16567853923578998,3.3822471532955594,2.945614690971615,6.493540383502983,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,6.1661,49.7498,2015.3354835510254,machine,N,1.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2828f89e9548dd3e1fb882527a31feb7e7aa2a823518362f60d00066d2540cea
+oid sha256:44b83ff8a5a53bd4fb81e91558f3434d615560a7a24bf5a8ff80478f8179849e
 size 498618976