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: cosine
lr_scheduler_warmup_steps: 100
training_steps: 5000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.565	0.5051	100	0.5047
0.5258	1.0101	200	0.4888
0.496	1.5152	300	0.4695
0.4882	2.0202	400	0.4558
0.4839	2.5253	500	0.4531
0.4781	3.0303	600	0.4487
0.4715	3.5354	700	0.4446
0.4657	4.0404	800	0.4408
0.4582	4.5455	900	0.4397
0.4568	5.0505	1000	0.4379
0.4552	5.5556	1100	0.4427
0.451	6.0606	1200	0.4333
0.4512	6.5657	1300	0.4327
0.4441	7.0707	1400	0.4321
0.4453	7.5758	1500	0.4313
0.4422	8.0808	1600	0.4314
0.4405	8.5859	1700	0.4262
0.4427	9.0909	1800	0.4306
0.4362	9.5960	1900	0.4315
0.4306	10.1010	2000	0.4239
0.4328	10.6061	2100	0.4250
0.425	11.1111	2200	0.4272
0.4271	11.6162	2300	0.4312
0.4246	12.1212	2400	0.4259
0.424	12.6263	2500	0.4253
0.4209	13.1313	2600	0.4231
0.4204	13.6364	2700	0.4295
0.4135	14.1414	2800	0.4228
0.4162	14.6465	2900	0.4180
0.4169	15.1515	3000	0.4254
0.4136	15.6566	3100	0.4228
0.4102	16.1616	3200	0.4241
0.4107	16.6667	3300	0.4213
0.4104	17.1717	3400	0.4281
0.409	17.6768	3500	0.4240
0.4083	18.1818	3600	0.4264
0.405	18.6869	3700	0.4260
0.4035	19.1919	3800	0.4265
0.4054	19.6970	3900	0.4271
0.4047	20.2020	4000	0.4305
0.4031	20.7071	4100	0.4304
0.4044	21.2121	4200	0.4289
0.4016	21.7172	4300	0.4297
0.4005	22.2222	4400	0.4275
0.4084	22.7273	4500	0.4291
0.4026	23.2323	4600	0.4284
0.402	23.7374	4700	0.4288
0.4002	24.2424	4800	0.4294
0.401	24.7475	4900	0.4298
0.398	25.2525	5000	0.4299

Shaju07/urdu_tts_0.1

urdu_tts_0.1