elselse's picture
CIRCL/cwe-parent-vulnerability-classification-roberta-base
dd65ad2 verified
|
raw
history blame
4.41 kB
metadata
library_name: transformers
license: mit
base_model: roberta-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: cwe-parent-vulnerability-classification-roberta-base
    results: []

cwe-parent-vulnerability-classification-roberta-base

This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9131
  • Accuracy: 0.7701
  • F1 Macro: 0.4179

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: 1e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 40

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Macro
3.2726 1.0 25 3.1430 0.0230 0.0041
3.214 2.0 50 2.9861 0.0230 0.0041
3.1457 3.0 75 2.9949 0.0115 0.0019
3.0447 4.0 100 3.0090 0.1149 0.0265
3.0588 5.0 125 2.9652 0.0230 0.0039
2.9336 6.0 150 2.9089 0.4828 0.1081
2.9729 7.0 175 2.9005 0.1264 0.0606
2.812 8.0 200 2.9174 0.3563 0.1788
2.6587 9.0 225 2.8268 0.3563 0.1414
2.5464 10.0 250 2.8296 0.3103 0.1339
2.4379 11.0 275 2.7762 0.2989 0.1554
2.2741 12.0 300 2.7595 0.4598 0.1745
2.1793 13.0 325 2.7483 0.4943 0.1826
2.0085 14.0 350 2.6646 0.4713 0.2136
1.9313 15.0 375 2.6414 0.6092 0.2916
1.7534 16.0 400 2.5186 0.6552 0.3345
1.6187 17.0 425 2.3736 0.6552 0.3381
1.5568 18.0 450 2.2908 0.6667 0.3391
1.4627 19.0 475 2.4101 0.6437 0.3356
1.2964 20.0 500 2.2791 0.6782 0.3525
1.2236 21.0 525 2.1636 0.6667 0.3403
1.1237 22.0 550 2.1584 0.6897 0.3397
1.0589 23.0 575 2.1262 0.6782 0.3535
0.952 24.0 600 2.1252 0.6782 0.3504
0.9137 25.0 625 2.0899 0.6667 0.3656
0.878 26.0 650 1.9915 0.7126 0.4012
0.8073 27.0 675 1.9856 0.7356 0.3857
0.7588 28.0 700 1.9613 0.7356 0.3737
0.7114 29.0 725 1.9789 0.7701 0.4103
0.6728 30.0 750 1.9131 0.7701 0.4179
0.6651 31.0 775 2.0236 0.7701 0.4231
0.5979 32.0 800 2.0366 0.7701 0.4668
0.5946 33.0 825 2.0026 0.7931 0.4478
0.5395 34.0 850 2.0010 0.8046 0.4544
0.5301 35.0 875 1.9332 0.8046 0.4500
0.5216 36.0 900 1.9965 0.8161 0.4966
0.497 37.0 925 1.9930 0.8161 0.4639
0.5149 38.0 950 1.9813 0.8161 0.4582
0.5022 39.0 975 1.9775 0.8046 0.4667
0.4892 40.0 1000 1.9643 0.8161 0.4688

Framework versions

  • Transformers 4.55.4
  • Pytorch 2.7.1+cu126
  • Datasets 4.0.0
  • Tokenizers 0.21.2