learning_rate: 3e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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_steps: 500
training_steps: 8000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.5591	0.8711	1000	0.5155
0.5348	1.7422	2000	0.4937
0.5155	2.6132	3000	0.4782
0.5127	3.4843	4000	0.4735
0.4908	4.3554	5000	0.4690
0.4951	5.2265	6000	0.4654
0.4935	6.0976	7000	0.4617
0.4988	6.9686	8000	0.4611

rezjhn/speech_T5_jahani_Finetune_Persian

speech_T5_jahani_Finetune_Persian