learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 1968
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Use 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: 0.3
num_epochs: 15

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.8571	3	1.0983	0.3103	0.2990
No log	2.0	7	1.0947	0.4828	0.4047
1.0979	2.8571	10	1.0935	0.3793	0.2808
1.0979	4.0	14	1.0766	0.4138	0.3723
1.0979	4.8571	17	1.0710	0.4483	0.3853
1.064	6.0	21	1.0185	0.4483	0.4447
1.064	6.8571	24	1.0051	0.4483	0.4
1.064	8.0	28	1.0496	0.4828	0.4425
0.9118	8.8571	31	1.0056	0.5172	0.5110
0.9118	10.0	35	1.1071	0.5172	0.5232
0.9118	10.8571	38	1.0749	0.4828	0.4849
0.8278	12.0	42	1.0614	0.4483	0.4537
0.8278	12.8571	45	1.0562	0.4828	0.4858

sarasarasara/hubert-base-ls960-finetuned-bmd-V1-20241110_112632-LOSO-section-out1

hubert-base-ls960-finetuned-bmd-V1-20241110_112632-LOSO-section-out1