learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
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: 100
training_steps: 5000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.6313	0.3772	100	0.5546
0.5936	0.7544	200	0.5346
0.5665	1.1282	300	0.5138
0.5564	1.5054	400	0.5165
0.5446	1.8826	500	0.5033
0.5416	2.2565	600	0.4978
0.5365	2.6337	700	0.4919
0.5023	3.0075	800	0.4927
0.5223	3.3847	900	0.4952
0.5238	3.7619	1000	0.4921
0.5217	4.1358	1100	0.4857
0.5052	4.5130	1200	0.4969
0.5107	4.8901	1300	0.4815
0.5057	5.2640	1400	0.4825
0.5018	5.6412	1500	0.4766
0.4912	6.0151	1600	0.4766
0.5018	6.3923	1700	0.4800
0.4987	6.7694	1800	0.4771
0.4954	7.1433	1900	0.4739
0.4926	7.5205	2000	0.4789
0.4913	7.8977	2100	0.4729
0.491	8.2716	2200	0.4724
0.4879	8.6488	2300	0.4704
0.4688	9.0226	2400	0.4755
0.4817	9.3998	2500	0.4689
0.4824	9.7770	2600	0.4739
0.4805	10.1509	2700	0.4735
0.4782	10.5281	2800	0.4724
0.4797	10.9052	2900	0.4728
0.4704	11.2791	3000	0.4721
0.4802	11.6563	3100	0.4685
0.4539	12.0302	3200	0.4687
0.4696	12.4074	3300	0.4713
0.4656	12.7845	3400	0.4705
0.4672	13.1584	3500	0.4677
0.4643	13.5356	3600	0.4722
0.4659	13.9128	3700	0.4654
0.4694	14.2867	3800	0.4681
0.4638	14.6638	3900	0.4702
0.4447	15.0377	4000	0.4675
0.4628	15.4149	4100	0.4696
0.46	15.7921	4200	0.4678
0.4592	16.1660	4300	0.4705
0.4616	16.5431	4400	0.4680
0.4578	16.9203	4500	0.4696
0.4576	17.2942	4600	0.4678
0.4555	17.6714	4700	0.4706
0.4394	18.0453	4800	0.4710
0.4485	18.4224	4900	0.4702
0.4563	18.7996	5000	0.4719

kaab4321/speecht5_finetuned_kaab_tts_ur_5000

speecht5_finetuned_kaab_tts_ur_5000