learning_rate: 0.0003
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
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: 500
num_epochs: 30
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
6.7643	1.7544	400	3.3975	1.0
3.2365	3.5088	800	3.0763	0.9975
3.0169	5.2632	1200	2.3831	1.0191
1.4481	7.0175	1600	0.8834	0.5629
0.8228	8.7719	2000	0.6189	0.3965
0.6329	10.5263	2400	0.5400	0.3333
0.5043	12.2807	2800	0.5054	0.2831
0.4179	14.0351	3200	0.4820	0.2625
0.3599	15.7895	3600	0.4979	0.2406
0.3152	17.5439	4000	0.4816	0.2286
0.2778	19.2982	4400	0.4848	0.2183
0.2557	21.0526	4800	0.4710	0.2172
0.2285	22.8070	5200	0.5168	0.2053
0.2113	24.5614	5600	0.5015	0.2013
0.1992	26.3158	6000	0.5347	0.1989
0.1846	28.0702	6400	0.5403	0.1974
0.1804	29.8246	6800	0.5489	0.1957

Tashi-Projects/Dzo_ASR_xlsr_53

Dzo_ASR_xlsr_53