learning_rate: 0.0003
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 64
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: 400
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Wer
0.2538	0.9791	41	0.2886	0.0212	0.1134
0.1828	1.9791	82	0.3033	0.0212	0.1182
0.1233	2.9791	123	0.3724	0.0212	0.1248
0.1182	3.9791	164	0.4213	0.0212	0.1399
0.1181	4.9791	205	0.4813	0.0212	0.1417
0.1273	5.9791	246	0.5741	0.0212	0.1553
0.1237	6.9791	287	0.6128	0.0212	0.1759
0.1176	7.9791	328	0.6665	0.0212	0.1823
0.1076	8.9791	369	0.7048	0.0212	0.1929
0.1357	9.9791	410	0.7453	0.0212	0.2339

charlesfrye/ap-fEz97qWiEaKtCs943k0PtZ

ap-fEz97qWiEaKtCs943k0PtZ