learning_rate: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
0.7405	1.0	91	0.6308	44.1897
0.3613	2.0	182	0.6133	39.8814
0.1901	3.0	273	0.6772	39.4664
0.0998	4.0	364	0.7300	41.0672
0.0567	5.0	455	0.7617	40.6917
0.0386	6.0	546	0.8190	41.4032
0.0283	7.0	637	0.8305	40.2767
0.0219	8.0	728	0.8507	39.8617
0.0185	9.0	819	0.8770	43.2411
0.0179	9.8950	900	0.9390	41.2253

santyzenith/UDA-LIDI-Whisper-large-ECU-911

UDA-LIDI-Whisper-large-ECU-911