learning_rate: 3e-05
train_batch_size: 1
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
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_steps: 50
num_epochs: 50
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.8062	1.0	5	0.7544
0.7415	2.0	10	0.6804
0.6828	3.0	15	0.6632
0.6771	4.0	20	0.6502
0.5912	5.0	25	0.6282
0.567	6.0	30	0.6299
0.5648	7.0	35	0.6188
0.5267	8.0	40	0.6177
0.551	9.0	45	0.6224
0.5704	10.0	50	0.6084
0.5177	11.0	55	0.6075
0.5144	12.0	60	0.6153
0.5041	13.0	65	0.6036
0.5	14.0	70	0.6086
0.4854	15.0	75	0.6018
0.5063	16.0	80	0.6035
0.4768	17.0	85	0.5934
0.4881	18.0	90	0.5961
0.4849	19.0	95	0.5856
0.4699	20.0	100	0.5960
0.49	21.0	105	0.5984
0.4749	22.0	110	0.5915
0.4746	23.0	115	0.5991
0.4744	24.0	120	0.5872
0.4599	25.0	125	0.5841
0.4628	26.0	130	0.5869
0.4704	27.0	135	0.5857
0.4602	28.0	140	0.5927
0.4547	29.0	145	0.5879
0.4533	30.0	150	0.5828
0.4591	31.0	155	0.5825
0.4543	32.0	160	0.5825
0.4628	33.0	165	0.5796
0.4658	34.0	170	0.5750
0.4578	35.0	175	0.5789
0.4437	36.0	180	0.5797
0.448	37.0	185	0.5861
0.457	38.0	190	0.5853
0.4523	39.0	195	0.5796
0.4564	40.0	200	0.5821

kavinda123321/speecht5_finetuned_sinhala_mahinda

speecht5_finetuned_sinhala_mahinda