learning_rate: 0.001
train_batch_size: 256
eval_batch_size: 1
seed: 914
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: 0.1
num_epochs: 10.0
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
4.6869	1.0	523	4.1199	0.1960
3.2423	2.0	1046	2.2824	0.5047
2.4164	3.0	1569	1.4862	0.6816
1.8625	4.0	2092	0.9794	0.7917
1.5637	5.0	2615	0.7048	0.8490
1.265	6.0	3138	0.5389	0.8862
1.0888	7.0	3661	0.4364	0.9101
0.9296	8.0	4184	0.3617	0.9265
0.8066	9.0	4707	0.3207	0.9353
0.7675	10.0	5230	0.2981	0.9405

yangwang825/xvector-voxceleb1

xvector-voxceleb1