learning_rate: 2e-05
train_batch_size: 4
eval_batch_size: 4
seed: 1968
gradient_accumulation_steps: 4
total_train_batch_size: 16
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
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	6	1.0949	0.3333	0.1667
1.0986	2.0	12	1.0883	0.4583	0.3657
1.0986	3.0	18	1.0816	0.4583	0.3913
1.0877	4.0	24	1.0726	0.4167	0.3620
1.0682	5.0	30	1.0597	0.4583	0.3913
1.0682	6.0	36	1.0307	0.5417	0.5097
1.0418	7.0	42	1.0012	0.5417	0.5507
1.0418	8.0	48	0.9725	0.5417	0.5442
1.0157	9.0	54	0.9712	0.4583	0.4237
0.9868	10.0	60	0.9744	0.4167	0.3660

sarasarasara/hubert-base-ls960-3kfoldfull-finetuned-bmd-V1-10-20250824_130250-LOSO-sec-out1

hubert-base-ls960-3kfoldfull-finetuned-bmd-V1-10-20250824_130250-LOSO-sec-out1