learning_rate: 3e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
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
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6944	0.9915	29	0.6913	0.5758
0.6847	1.9829	58	0.6920	0.4848
0.6672	2.9744	87	0.6705	0.5657
0.6773	4.0	117	0.6847	0.5253
0.6815	4.9915	146	0.6864	0.4949
0.6895	5.9829	175	0.6891	0.4747
0.6939	6.9744	204	0.6839	0.4848
0.6607	8.0	234	0.6798	0.5556
0.6501	8.9915	263	0.6779	0.5657
0.6391	9.9145	290	0.6633	0.6465

penkichiai/Riku_Binary_Wav2Vec

Riku_Binary_Wav2Vec