learning_rate: 8e-05
train_batch_size: 64
eval_batch_size: 64
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.98) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy Score	F1 Score	Precision Score	Recall Score
0.6768	1.0	342	0.6130	0.6358	0.5728	0.5315	0.6210
0.5902	2.0	684	0.5828	0.6654	0.5421	0.4311	0.7301
0.5346	3.0	1026	0.5995	0.6585	0.4744	0.3355	0.8096
0.4583	4.0	1368	0.6115	0.6812	0.6085	0.5394	0.6979
0.3722	5.0	1710	0.6749	0.6482	0.6197	0.6239	0.6156
0.2896	6.0	2052	0.8197	0.6490	0.6087	0.5944	0.6237
0.2234	7.0	2394	0.9451	0.6490	0.6019	0.5777	0.6282
0.1655	8.0	2736	1.1632	0.6354	0.6115	0.6247	0.5989
0.1151	9.0	3078	1.4168	0.6387	0.6063	0.6056	0.6070
0.0684	10.0	3420	2.0516	0.6369	0.6091	0.6159	0.6025

mrm8488/ModernBERT-base-ft-code-defect-detection-10e-4k

ModernBERT-base-ft-code-defect-detection-10e-4k