cedricbonhomme's picture
CIRCL/cwe-parent-vulnerability-classification-roberta-base-roberta-base
3ee54af verified
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-roberta-base
    results: []

cwe-parent-vulnerability-classification-roberta-base-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: 1.3755
  • Accuracy: 0.6603
  • F1 Macro: 0.4616

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_FUSED 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
2.9549 1.0 238 2.9056 0.0948 0.0729
2.2865 2.0 476 1.9760 0.4946 0.3041
1.8517 3.0 714 1.7010 0.5114 0.3522
1.6439 4.0 952 1.5457 0.6074 0.3826
1.3475 5.0 1190 1.5154 0.5894 0.3608
1.1372 6.0 1428 1.4379 0.6327 0.4183
1.0323 7.0 1666 1.3955 0.6411 0.4184
0.8662 8.0 1904 1.3755 0.6603 0.4616
0.8135 9.0 2142 1.4626 0.6807 0.4703
0.632 10.0 2380 1.4197 0.6999 0.4439
0.5727 11.0 2618 1.4083 0.6795 0.4878
0.5429 12.0 2856 1.5234 0.6651 0.4823
0.3597 13.0 3094 1.5866 0.7107 0.4995
0.3076 14.0 3332 1.6262 0.7191 0.5243
0.2458 15.0 3570 1.7271 0.6963 0.5259
0.2052 16.0 3808 1.7799 0.7011 0.4556
0.1801 17.0 4046 1.7717 0.7179 0.4983
0.187 18.0 4284 2.0014 0.7239 0.5273
0.1473 19.0 4522 1.9999 0.7419 0.5388
0.1198 20.0 4760 1.9328 0.7275 0.5336
0.152 21.0 4998 2.0637 0.7407 0.4759
0.0692 22.0 5236 2.2153 0.7647 0.5553
0.0632 23.0 5474 2.1253 0.7431 0.5381
0.069 24.0 5712 2.2856 0.7587 0.5443
0.0472 25.0 5950 2.3607 0.7611 0.5286
0.0452 26.0 6188 2.4693 0.7539 0.5191
0.0388 27.0 6426 2.4699 0.7587 0.5550
0.0412 28.0 6664 2.5062 0.7659 0.5332
0.0419 29.0 6902 2.4443 0.7551 0.5488
0.0238 30.0 7140 2.5642 0.7479 0.5487
0.0616 31.0 7378 2.5451 0.7623 0.5511
0.0163 32.0 7616 2.6758 0.7599 0.5450
0.028 33.0 7854 2.6806 0.7671 0.5432
0.0147 34.0 8092 2.6815 0.7647 0.5518
0.0251 35.0 8330 2.7046 0.7611 0.5470
0.0151 36.0 8568 2.6610 0.7527 0.5440
0.0128 37.0 8806 2.7269 0.7551 0.5426
0.0421 38.0 9044 2.7759 0.7515 0.5437
0.0259 39.0 9282 2.7239 0.7587 0.5444
0.0046 40.0 9520 2.7196 0.7599 0.5448

Framework versions

  • Transformers 4.57.1
  • Pytorch 2.9.1+cu128
  • Datasets 4.4.1
  • Tokenizers 0.22.1