learning_rate: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
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
num_epochs: 3
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Cer	Validation Loss
3.1316	0.2626	500	327.6237	1.4389
1.2083	0.5252	1000	456.3455	0.9819
0.9269	0.7878	1500	737.9578	0.8079
0.7618	1.0504	2000	966.5418	0.7155
0.5428	1.3130	2500	665.7924	0.6660
0.5139	1.5756	3000	899.3139	0.6320
0.4948	1.8382	3500	965.0479	0.6049
0.4122	2.1008	4000	942.7040	0.5902
0.3145	2.3634	4500	969.4258	0.5819
0.2576	2.6261	5000	890.9343	0.5805

CianKim/whisper-medium.en-merged_dataset

whisper-medium.en-merged_dataset