learning_rate: 3e-05
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: 16
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Model Preparation Time	Wer
0.4516	1.0	250	0.2822	0.0073	0.1329
0.1981	2.0	500	0.2433	0.0073	0.1390
0.1437	3.0	750	0.2299	0.0073	0.1183
0.1073	4.0	1000	0.2392	0.0073	0.1261
0.0825	5.0	1250	0.2526	0.0073	0.1339
0.063	6.0	1500	0.2545	0.0073	0.1262
0.0496	7.0	1750	0.2777	0.0073	0.1244
0.0375	8.0	2000	0.2883	0.0073	0.1308
0.0289	9.0	2250	0.2757	0.0073	0.1129
0.0216	10.0	2500	0.3027	0.0073	0.1218
0.0153	11.0	2750	0.3247	0.0073	0.1199
0.0117	12.0	3000	0.3193	0.0073	0.1147
0.0059	13.0	3250	0.3347	0.0073	0.1158
0.0023	14.0	3500	0.3520	0.0073	0.1178
0.0011	15.0	3750	0.3593	0.0073	0.1160
0.0007	15.9365	3984	0.3547	0.0073	0.1169

dhaval0108/whisper-large-v3-turbo-finetuned-3e5-lr

ap-u2ve4vNEqG8dHywtw4QDVP