learning_rate: 2e-05
train_batch_size: 4
eval_batch_size: 4
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: cosine_with_restarts
lr_scheduler_warmup_steps: 128
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	F1 Class 0	F1 Class 1	F1 Class 2	F1 Class 3	F1 Class 4
1.6114	1.0	128	1.5195	0.2734	0.2457	0.3722	0.2734	0.0	0.2645	0.0	0.0	0.4524
1.4553	2.0	256	1.3363	0.4844	0.3835	0.4706	0.4844	0.2	0.2051	0.1111	0.0	0.6832
1.1825	3.0	384	1.3479	0.4375	0.4169	0.4348	0.4375	0.3333	0.0909	0.24	0.3462	0.6116
0.9147	4.0	512	1.6561	0.4531	0.4482	0.4703	0.4531	0.3478	0.2083	0.2581	0.2759	0.656
0.8018	5.0	640	1.9149	0.4453	0.4427	0.4550	0.4453	0.3077	0.1765	0.3111	0.4	0.6116

matiashoyl/modernbert-match-user-52295

modernbert-match-user-52295