learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 4
seed: 1968
gradient_accumulation_steps: 4
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: 0.1
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	6	0.6795	0.5652	0.5145	0.6430	0.5652
0.6429	2.0	12	0.6508	0.6957	0.6922	0.7133	0.6957
0.6429	3.0	18	0.5901	0.7391	0.7288	0.7686	0.7391
0.5306	4.0	24	0.6976	0.6522	0.6441	0.6783	0.6522
0.4812	5.0	30	0.6430	0.6957	0.6590	0.8078	0.6957
0.4812	6.0	36	0.6919	0.6522	0.5963	0.7913	0.6522
0.4336	7.0	42	0.4892	0.7826	0.7826	0.7856	0.7826
0.4336	8.0	48	0.4931	0.7826	0.7826	0.7856	0.7826
0.3751	8.3810	50	0.4886	0.7826	0.7826	0.7856	0.7826

sarasarasara/hubert-base-ls960-2clsfinetuned-bmd-V1-epo10-20250201_141430-LOSO-section-out4

hubert-base-ls960-2clsfinetuned-bmd-V1-epo10-20250201_141430-LOSO-section-out4