learning_rate: 5e-06
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
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
lr_scheduler_warmup_ratio: 0.05
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss	F1 Macro
0.5788	1.0	1534	0.5783	0.0
0.5675	2.0	3068	0.5714	0.1304
0.5424	3.0	4602	0.5386	0.1952
0.516	4.0	6136	0.5493	0.2382
0.4922	5.0	7670	0.6015	0.2394
0.4744	6.0	9204	0.5404	0.3192
0.4494	7.0	10738	0.5746	0.3733
0.4353	8.0	12272	0.5689	0.3396
0.4147	9.0	13806	0.5695	0.3608
0.4006	10.0	15340	0.6441	0.3871
0.3843	11.0	16874	0.5938	0.3888
0.3763	12.0	18408	0.6159	0.4054
0.3606	13.0	19942	0.5831	0.4042
0.3478	14.0	21476	0.6116	0.4056
0.3447	15.0	23010	0.6169	0.3999
0.3215	16.0	24544	0.6441	0.4150
0.3196	17.0	26078	0.6530	0.4129
0.3184	18.0	27612	0.6634	0.4192
0.3065	19.0	29146	0.6791	0.4192
0.298	20.0	30680	0.6827	0.4188

DayCardoso/modernbert-base-multi-head

modernbert-base-multi-head