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: 1500
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.33	99.6154	100	0.3955
0.3199	199.6154	200	0.4201
0.3083	299.6154	300	0.3931
0.2953	399.6154	400	0.3909
0.2892	499.6154	500	0.4071
0.2813	599.6154	600	0.3986
0.2789	699.6154	700	0.4070
0.2661	799.6154	800	0.4091
0.2605	899.6154	900	0.4065
0.2586	999.6154	1000	0.4291
0.2549	1099.6154	1100	0.4386
0.253	1199.6154	1200	0.4261
0.2492	1299.6154	1300	0.4205
0.2519	1399.6154	1400	0.4168
0.2473	1499.6154	1500	0.4127

tahmidkhanalim/Bangla-tts-small

Bangla-tts-small