learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 16
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: 20

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	15	0.5181	0.7481
No log	2.0	30	0.3811	0.8373
No log	3.0	45	0.6849	0.6865
No log	4.0	60	0.4782	0.8611
No log	5.0	75	0.2552	0.9376
No log	6.0	90	0.3630	0.9127
0.2889	7.0	105	0.4094	0.8618
0.2889	8.0	120	0.3934	0.8997
0.2889	9.0	135	0.3548	0.9376
0.2889	10.0	150	0.4377	0.8746
0.2889	11.0	165	0.4106	0.9126
0.2889	12.0	180	0.4450	0.8997
0.2889	13.0	195	0.3728	0.9376
0.0041	14.0	210	0.3698	0.9252
0.0041	15.0	225	0.3708	0.9252
0.0041	16.0	240	0.3696	0.9252
0.0041	17.0	255	0.3703	0.9252
0.0041	18.0	270	0.3718	0.9252
0.0041	19.0	285	0.3722	0.9252
0.0	20.0	300	0.3695	0.9252

travis-simon/ModernBERT-regulation-classifier

ModernBERT-regulation-classifier