cwe-parent-vulnerability-classification-bert-base-uncased

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

• Loss: 2.9385
• Accuracy: 0.4270
• F1 Macro: 0.2048

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
3.2751	1.0	25	3.3057	0.0112	0.0019
3.1518	2.0	50	3.1378	0.0449	0.0337
3.0997	3.0	75	3.2138	0.0674	0.0376
2.9858	4.0	100	3.1921	0.1348	0.0806
2.9764	5.0	125	3.1470	0.2584	0.1308
2.8564	6.0	150	3.2075	0.3708	0.1465
2.8474	7.0	175	3.1799	0.3596	0.1653
2.7354	8.0	200	3.1618	0.3483	0.1412
2.6452	9.0	225	3.1248	0.3258	0.1531
2.5802	10.0	250	3.1154	0.3371	0.1488
2.5078	11.0	275	3.1547	0.3820	0.1712
2.4203	12.0	300	3.1410	0.3483	0.1549
2.3624	13.0	325	3.1409	0.4045	0.1776
2.3642	14.0	350	3.0964	0.2809	0.1496
2.2259	15.0	375	3.0960	0.3708	0.1904
2.1874	16.0	400	3.0170	0.3146	0.1653
2.15	17.0	425	3.0944	0.3146	0.1452
2.1051	18.0	450	3.0225	0.3258	0.1807
1.988	19.0	475	3.0687	0.3820	0.1539
1.9716	20.0	500	3.0054	0.3820	0.1675
1.9034	21.0	525	2.9834	0.3820	0.1985
1.8538	22.0	550	3.0251	0.3933	0.1942
1.8294	23.0	575	3.0231	0.3708	0.1579
1.7436	24.0	600	2.9719	0.4045	0.1976
1.7088	25.0	625	2.9701	0.4157	0.2138
1.7028	26.0	650	2.9724	0.4607	0.2250
1.6962	27.0	675	2.9385	0.4270	0.2048
1.5973	28.0	700	2.9636	0.4494	0.1904
1.5754	29.0	725	2.9441	0.5393	0.2116
1.5279	30.0	750	2.9785	0.5506	0.2373
1.5802	31.0	775	2.9711	0.5618	0.2346
1.4479	32.0	800	2.9884	0.5730	0.2335
1.484	33.0	825	3.0117	0.5730	0.2550
1.4243	34.0	850	2.9759	0.5843	0.2408
1.4473	35.0	875	2.9626	0.5955	0.2692
1.3875	36.0	900	2.9673	0.5843	0.2342
1.4214	37.0	925	2.9887	0.5843	0.2564
1.373	38.0	950	2.9894	0.6067	0.2728
1.3472	39.0	975	2.9805	0.5730	0.2311
1.336	40.0	1000	2.9836	0.5843	0.2439

Framework versions

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