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: 4.2511
Accuracy: 0.5683
F1 Macro: 0.2101

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: 64
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
num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro
5.6204	1.0	101	5.5246	0.0189	0.0004
5.4605	2.0	202	5.4081	0.0068	0.0005
5.4306	3.0	303	5.3191	0.0447	0.0045
5.3366	4.0	404	5.2692	0.0717	0.0049
5.2705	5.0	505	5.2310	0.0704	0.0096
5.1530	6.0	606	5.1756	0.0934	0.0136
4.9916	7.0	707	5.1084	0.2097	0.0299
4.8387	8.0	808	5.0626	0.2341	0.0419
4.7198	9.0	909	5.0164	0.2503	0.0616
4.6754	10.0	1010	4.9531	0.2963	0.0674
4.4443	11.0	1111	4.9144	0.3194	0.0714
4.3628	12.0	1212	4.8954	0.3315	0.0811
4.2481	13.0	1313	4.8476	0.3654	0.1104
4.1578	14.0	1414	4.7984	0.3775	0.1155
3.9924	15.0	1515	4.7600	0.4181	0.1226
3.9078	16.0	1616	4.7190	0.4263	0.1215
3.8065	17.0	1717	4.6783	0.4506	0.1442
3.7696	18.0	1818	4.6424	0.4696	0.1503
3.7075	19.0	1919	4.6157	0.4696	0.1438
3.5318	20.0	2020	4.5766	0.4736	0.1489
3.5248	21.0	2121	4.5494	0.4831	0.1463
3.5334	22.0	2222	4.5183	0.5101	0.1718
3.3713	23.0	2323	4.4923	0.5183	0.1595
3.2803	24.0	2424	4.4588	0.5223	0.1758
3.2246	25.0	2525	4.4311	0.5250	0.1932
3.1723	26.0	2626	4.4115	0.5359	0.1911
3.0648	27.0	2727	4.3898	0.5359	0.1986
2.9372	28.0	2828	4.3769	0.5426	0.1994
3.0113	29.0	2929	4.3596	0.5494	0.1968
2.9797	30.0	3030	4.3321	0.5413	0.1882
2.9339	31.0	3131	4.3254	0.5453	0.1944
2.8733	32.0	3232	4.3052	0.5521	0.1934
2.8051	33.0	3333	4.2951	0.5629	0.2121
2.8297	34.0	3434	4.2923	0.5589	0.2049
2.7814	35.0	3535	4.2770	0.5616	0.2079
2.7509	36.0	3636	4.2605	0.5670	0.2107
2.7396	37.0	3737	4.2677	0.5670	0.2128
2.7384	38.0	3838	4.2520	0.5670	0.2099
2.7081	39.0	3939	4.2548	0.5670	0.2115
2.7587	40.0	4040	4.2511	0.5683	0.2101

Framework versions

Transformers 5.13.0
Pytorch 2.12.1+cu130
Datasets 4.8.5
Tokenizers 0.22.2

Loading…

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-05

train_batch_size: 64

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

num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro
5.6204	1.0	101	5.5246	0.0189	0.0004
5.4605	2.0	202	5.4081	0.0068	0.0005
5.4306	3.0	303	5.3191	0.0447	0.0045
5.3366	4.0	404	5.2692	0.0717	0.0049
5.2705	5.0	505	5.2310	0.0704	0.0096
5.1530	6.0	606	5.1756	0.0934	0.0136
4.9916	7.0	707	5.1084	0.2097	0.0299
4.8387	8.0	808	5.0626	0.2341	0.0419
4.7198	9.0	909	5.0164	0.2503	0.0616
4.6754	10.0	1010	4.9531	0.2963	0.0674
4.4443	11.0	1111	4.9144	0.3194	0.0714
4.3628	12.0	1212	4.8954	0.3315	0.0811
4.2481	13.0	1313	4.8476	0.3654	0.1104
4.1578	14.0	1414	4.7984	0.3775	0.1155
3.9924	15.0	1515	4.7600	0.4181	0.1226
3.9078	16.0	1616	4.7190	0.4263	0.1215
3.8065	17.0	1717	4.6783	0.4506	0.1442
3.7696	18.0	1818	4.6424	0.4696	0.1503
3.7075	19.0	1919	4.6157	0.4696	0.1438
3.5318	20.0	2020	4.5766	0.4736	0.1489
3.5248	21.0	2121	4.5494	0.4831	0.1463
3.5334	22.0	2222	4.5183	0.5101	0.1718
3.3713	23.0	2323	4.4923	0.5183	0.1595
3.2803	24.0	2424	4.4588	0.5223	0.1758
3.2246	25.0	2525	4.4311	0.5250	0.1932
3.1723	26.0	2626	4.4115	0.5359	0.1911
3.0648	27.0	2727	4.3898	0.5359	0.1986
2.9372	28.0	2828	4.3769	0.5426	0.1994
3.0113	29.0	2929	4.3596	0.5494	0.1968
2.9797	30.0	3030	4.3321	0.5413	0.1882
2.9339	31.0	3131	4.3254	0.5453	0.1944
2.8733	32.0	3232	4.3052	0.5521	0.1934
2.8051	33.0	3333	4.2951	0.5629	0.2121
2.8297	34.0	3434	4.2923	0.5589	0.2049
2.7814	35.0	3535	4.2770	0.5616	0.2079
2.7509	36.0	3636	4.2605	0.5670	0.2107
2.7396	37.0	3737	4.2677	0.5670	0.2128
2.7384	38.0	3838	4.2520	0.5670	0.2099
2.7081	39.0	3939	4.2548	0.5670	0.2115
2.7587	40.0	4040	4.2511	0.5683	0.2101

Framework versions

Transformers 5.13.0

Pytorch 2.12.1+cu130

Datasets 4.8.5

Tokenizers 0.22.2

CIRCL/cwe-parent-vulnerability-classification-roberta-base

cwe-parent-vulnerability-classification-roberta-base

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

cwe-parent-vulnerability-classification-roberta-base

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions