learning_rate: 0.0004
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use 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: 132
num_epochs: 16
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
No log	1.0	88	0.0818	50.4915
0.9011	2.0	176	0.0692	30.5630
0.1774	3.0	264	0.0428	25.5585
0.0484	4.0	352	0.0953	27.9714
0.0393	5.0	440	0.0466	16.0858
0.0488	6.0	528	0.0490	21.5371
0.024	7.0	616	0.0281	18.0518
0.0076	8.0	704	0.0316	9.0259
0.0076	9.0	792	0.0253	13.2261
0.0023	10.0	880	0.0269	10.8132
0.0011	11.0	968	0.0313	10.0089
0.0002	12.0	1056	0.0364	10.0089
0.0003	13.0	1144	0.0350	10.9920
0.0	14.0	1232	0.0336	10.9920
0.0	15.0	1320	0.0335	10.9920
0.0	16.0	1408	0.0334	10.9026

susmitabhatt/whisper-a-nomi-16

whisper-a-nomi-16