learning_rate: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 1968
gradient_accumulation_steps: 4
total_train_batch_size: 32
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: 30
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	3	1.0946	0.3333	0.1667
No log	2.0	6	1.0941	0.3333	0.1667
No log	3.0	9	1.0928	0.3333	0.1839
1.0958	4.0	12	1.0911	0.375	0.2778
1.0958	5.0	15	1.0893	0.4583	0.3626
1.0958	6.0	18	1.0877	0.4167	0.3375
1.0877	7.0	21	1.0861	0.5417	0.4533
1.0877	8.0	24	1.0840	0.5	0.4176
1.0877	9.0	27	1.0814	0.5	0.4176
1.0764	10.0	30	1.0781	0.5	0.4176
1.0764	11.0	33	1.0744	0.5	0.4176
1.0764	12.0	36	1.0694	0.5417	0.4539
1.0764	13.0	39	1.0638	0.5417	0.4539
1.0655	14.0	42	1.0571	0.5417	0.4539
1.0655	15.0	45	1.0501	0.5417	0.4539
1.0655	16.0	48	1.0426	0.5	0.4127
1.0437	17.0	51	1.0357	0.5	0.4127
1.0437	18.0	54	1.0292	0.5	0.4127
1.0437	19.0	57	1.0221	0.4583	0.3780
1.0197	20.0	60	1.0151	0.5	0.4176
1.0197	21.0	63	1.0088	0.5417	0.4533
1.0197	22.0	66	1.0039	0.5417	0.4533
1.0197	23.0	69	0.9989	0.5417	0.4533
0.9988	24.0	72	0.9927	0.5417	0.4533
0.9988	25.0	75	0.9884	0.5417	0.4533
0.9988	26.0	78	0.9851	0.5417	0.4533
0.9709	27.0	81	0.9839	0.5417	0.4533
0.9709	28.0	84	0.9816	0.5417	0.4444
0.9709	29.0	87	0.9806	0.5417	0.4444
0.9614	30.0	90	0.9806	0.5417	0.4444

sarasarasara/hubert-base-superb-er-3kfoldfull40-finetuned-bmd-20250824_112936-LOSO-section-out1

hubert-base-superb-er-3kfoldfull40-finetuned-bmd-20250824_112936-LOSO-section-out1