Text Classification
Transformers
Safetensors
roberta
Generated from Trainer
text-embeddings-inference
Instructions to use martynattakit/vuln-classifier-roberta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use martynattakit/vuln-classifier-roberta with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="martynattakit/vuln-classifier-roberta")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("martynattakit/vuln-classifier-roberta") model = AutoModelForSequenceClassification.from_pretrained("martynattakit/vuln-classifier-roberta") - Notebooks
- Google Colab
- Kaggle
vuln-classifier-roberta
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4013
- Macro F1: 0.8501
- Accuracy: 0.9421
- F1 Cwe-119: 0.8587
- F1 Cwe-125: 0.9503
- F1 Cwe-190: 0.9399
- F1 Cwe-20: 0.8371
- F1 Cwe-22: 0.9738
- F1 Cwe-269: 0.6992
- F1 Cwe-276: 0.7857
- F1 Cwe-287: 0.8383
- F1 Cwe-306: 0.7506
- F1 Cwe-352: 0.9959
- F1 Cwe-362: 0.9023
- F1 Cwe-416: 0.9349
- F1 Cwe-434: 0.9558
- F1 Cwe-476: 0.946
- F1 Cwe-502: 0.9335
- F1 Cwe-77: 0.0
- F1 Cwe-78: 0.9127
- F1 Cwe-787: 0.8824
- F1 Cwe-79: 0.9949
- F1 Cwe-798: 0.9508
- F1 Cwe-862: 0.9078
- F1 Cwe-863: 0.6037
- F1 Cwe-89: 0.9975
- F1 Cwe-918: 0.9616
- F1 Cwe-94: 0.7404
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy | F1 Cwe-119 | F1 Cwe-125 | F1 Cwe-190 | F1 Cwe-20 | F1 Cwe-22 | F1 Cwe-269 | F1 Cwe-276 | F1 Cwe-287 | F1 Cwe-306 | F1 Cwe-352 | F1 Cwe-362 | F1 Cwe-416 | F1 Cwe-434 | F1 Cwe-476 | F1 Cwe-502 | F1 Cwe-77 | F1 Cwe-78 | F1 Cwe-787 | F1 Cwe-79 | F1 Cwe-798 | F1 Cwe-862 | F1 Cwe-863 | F1 Cwe-89 | F1 Cwe-918 | F1 Cwe-94 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.5894 | 1.0 | 4533 | 0.4616 | 0.8301 | 0.9306 | 0.8332 | 0.9354 | 0.9229 | 0.786 | 0.9725 | 0.6819 | 0.7456 | 0.8021 | 0.6949 | 0.9938 | 0.9167 | 0.9219 | 0.945 | 0.9428 | 0.9243 | 0.0 | 0.882 | 0.8481 | 0.9921 | 0.953 | 0.8953 | 0.5187 | 0.9964 | 0.963 | 0.6851 |
| 0.4632 | 2.0 | 9066 | 0.4053 | 0.8472 | 0.9402 | 0.864 | 0.9458 | 0.9438 | 0.8361 | 0.9752 | 0.7002 | 0.8017 | 0.8285 | 0.7254 | 0.9947 | 0.9019 | 0.9307 | 0.9488 | 0.9463 | 0.946 | 0.0 | 0.9014 | 0.886 | 0.9941 | 0.9533 | 0.8976 | 0.5628 | 0.9964 | 0.9631 | 0.7372 |
| 0.3786 | 3.0 | 13599 | 0.4013 | 0.8501 | 0.9421 | 0.8587 | 0.9503 | 0.9399 | 0.8371 | 0.9738 | 0.6992 | 0.7857 | 0.8383 | 0.7506 | 0.9959 | 0.9023 | 0.9349 | 0.9558 | 0.946 | 0.9335 | 0.0 | 0.9127 | 0.8824 | 0.9949 | 0.9508 | 0.9078 | 0.6037 | 0.9975 | 0.9616 | 0.7404 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.3
- Tokenizers 0.22.2
- Downloads last month
- 24
Model tree for martynattakit/vuln-classifier-roberta
Base model
FacebookAI/roberta-base