learning_rate: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 4
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer	Cer	Score
0.5996	0.5496	1000	0.5983	0.8222	0.4107	0.6165
0.4298	1.0989	2000	0.4846	0.5734	0.2759	0.4246
0.3923	1.6485	3000	0.4546	0.5380	0.2517	0.3949
0.2835	2.1979	4000	0.4413	0.4935	0.2347	0.3641
0.3116	2.7475	5000	0.4295	0.6399	0.3235	0.4817
0.2426	3.2968	6000	0.4358	0.6338	0.3496	0.4917
0.2553	3.8464	7000	0.4327	0.7159	0.3848	0.5504

anyantudre/waxal-whisper_small_multi_s42

waxal-whisper_small_multi_s42