learning_rate: 5e-06
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: 1000
training_steps: 20000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
1.1297	20.0	1000	0.5249
1.0651	40.0	2000	0.5058
1.0377	60.0	3000	0.4958
1.024	80.0	4000	0.4904
1.0095	100.0	5000	0.4870
1.0052	120.0	6000	0.4832
0.9984	140.0	7000	0.4830
0.9908	160.0	8000	0.4818
0.99	180.0	9000	0.4810
0.98	200.0	10000	0.4814
0.9765	220.0	11000	0.4793
0.971	240.0	12000	0.4786
0.9756	260.0	13000	0.4823
0.9703	280.0	14000	0.4792
0.9718	300.0	15000	0.4780
0.959	320.0	16000	0.4792
0.963	340.0	17000	0.4789
0.9639	360.0	18000	0.4789
0.9613	380.0	19000	0.4786
0.9577	400.0	20000	0.4771

Sameeroz/speecht5_finetuned_ar

speecht5_finetuned_ar