learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 128
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: 15
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	53	0.9703	0.6251
17.3847	2.0	106	0.7751	0.7252
17.3847	3.0	159	0.7489	0.7485
7.7728	4.0	212	0.8238	0.7496
7.7728	5.0	265	0.9404	0.7462
3.4824	6.0	318	0.9658	0.7519
3.4824	7.0	371	1.0534	0.7550
1.8705	8.0	424	1.0702	0.7611
1.8705	9.0	477	1.1512	0.7641
1.0919	10.0	530	1.1111	0.7534
1.0919	11.0	583	1.1713	0.7575
0.6133	12.0	636	1.2639	0.7529
0.6133	13.0	689	1.2832	0.7602
0.3116	14.0	742	1.3196	0.7553
0.3116	15.0	795	1.3248	0.7588

thiomajid/ModernBERT-large-Vulnerability-v0

ModernBERT-large-Vulnerability-v0