learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 16
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: 30

Training Loss	Epoch	Step	Validation Loss	Accuracy	Recall	Precision	F1	F Beta Score
0.6614	1.0	21	0.5243	0.8696	0.9636	0.8833	0.9217	0.9374
0.4503	2.0	42	0.3185	0.8696	0.8364	1.0	0.9109	0.8807
0.177	3.0	63	0.1697	0.9420	0.9273	1.0	0.9623	0.9485
0.0745	4.0	84	0.1861	0.9420	1.0	0.9322	0.9649	0.9781
0.021	5.0	105	0.1795	0.9275	0.9091	1.0	0.9524	0.9353
0.012	6.0	126	0.1064	0.9565	0.9636	0.9815	0.9725	0.9691
0.0019	7.0	147	0.0580	0.9565	0.9455	1.0	0.9720	0.9616
0.0014	8.0	168	0.4638	0.9420	1.0	0.9322	0.9649	0.9781
0.0013	9.0	189	0.5281	0.9565	1.0	0.9483	0.9735	0.9835
0.0002	10.0	210	0.0222	0.9855	0.9818	1.0	0.9908	0.9873
0.0	11.0	231	0.1426	0.9565	1.0	0.9483	0.9735	0.9835
0.0	12.0	252	0.0211	0.9855	0.9818	1.0	0.9908	0.9873
0.0	13.0	273	0.0166	1.0	1.0	1.0	1.0	1.0
0.0	14.0	294	0.0167	1.0	1.0	1.0	1.0	1.0
0.0	15.0	315	0.0173	1.0	1.0	1.0	1.0	1.0
0.0	16.0	336	0.0177	1.0	1.0	1.0	1.0	1.0

buelfhood/irplag_modernbert_ep30_bs16_lr1e-05_l1280_s42_ppn_loss

irplag_modernbert_ep30_bs16_lr1e-05_l1280_s42_ppn_loss