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
0.7252	1.0	7	0.6931
0.6444	2.0	14	0.6860
0.5948	3.0	21	0.6016
0.5453	4.0	28	0.5579
0.4945	5.0	35	0.5652
0.4792	6.0	42	0.5520
0.4424	7.0	49	0.5520
0.4285	8.0	56	0.5383
0.4263	9.0	63	0.5343
0.4223	10.0	70	0.5590
0.4107	11.0	77	0.5349
0.3957	12.0	84	0.5345
0.3983	13.0	91	0.5336
0.3981	14.0	98	0.5350
0.3954	15.0	105	0.5460
0.3836	16.0	112	0.5375
0.3791	17.0	119	0.5391
0.3874	18.0	126	0.5368
0.3728	19.0	133	0.5466
0.3695	20.0	140	0.5483
0.3678	21.0	147	0.5500
0.3664	22.0	154	0.5465
0.3766	23.0	161	0.5416
0.3762	24.0	168	0.5479
0.3854	25.0	175	0.5541
0.3655	26.0	182	0.5458
0.3652	27.0	189	0.5535
0.365	28.0	196	0.5521
0.3629	29.0	203	0.5479
0.3618	30.0	210	0.5587
0.3637	31.0	217	0.5665
0.3629	32.0	224	0.5560
0.3523	33.0	231	0.5606
0.354	34.0	238	0.5583
0.3582	35.0	245	0.5583
0.3507	36.0	252	0.5561
0.356	37.0	259	0.5651
0.3533	38.0	266	0.5664
0.352	39.0	273	0.5620
0.3489	40.0	280	0.5657
0.3569	41.0	287	0.5698
0.3466	42.0	294	0.5623
0.3697	42.9057	300	0.5627

kavinda123321/speecht5_finetuned_english_ranil

speecht5_finetuned_english_ranil