learning_rate: 0.0001
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
optimizer: Use 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: 800
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.9484	0.2558	100	0.4630
0.9733	0.5115	200	0.4284
0.9148	0.7673	300	0.4140
0.8979	1.0230	400	0.4069
0.8684	1.2788	500	0.3942
0.8347	1.5345	600	0.3873
0.8332	1.7903	700	0.3846
0.8391	2.0460	800	0.3807

Dawid511/speecht5_finetuned_librispeech_polish_epo3_batch2_gas2

speecht5_finetuned_librispeech_polish_epo3_batch2_gas2