learning_rate: 0.0005
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
training_steps: 25000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
0.5290	5.7339	2500	0.4228	39.4243
0.1859	11.4679	5000	0.4204	35.9643
0.0914	17.2018	7500	0.4188	35.1018
0.0749	22.9358	10000	0.4176	32.0580
0.0537	28.6697	12500	0.4198	31.0751
0.0206	34.4037	15000	0.4003	28.1466
0.0205	40.1376	17500	0.3931	27.6953
0.0150	45.8716	20000	0.3856	25.3285
0.0058	51.6055	22500	0.3831	23.8943
0.0040	57.3394	25000	0.3801	23.6235

Eimhin03/MCV_Fleurs_Combined_Irish_ASR_with_Aug2

MCV_Fleurs_Combined_Irish_ASR_with_Aug2