learning_rate: 5e-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 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: 5
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
0.3985	0.2458	5000	0.4006	100
0.3535	0.4917	10000	0.3515	41.9359
0.3329	0.7375	15000	0.3267	41.2601
0.3088	0.9834	20000	0.3122	40.8518
0.2702	1.2292	25000	0.3052	39.1540
0.2682	1.4750	30000	0.2963	39.5239
0.2606	1.7208	35000	0.2891	38.2537
0.2622	1.9667	40000	0.2837	38.0593
0.2164	2.2125	45000	0.2854	37.4512
0.222	2.4583	50000	0.2817	37.9314
0.2233	2.7042	55000	0.2788	37.6204
0.2218	2.9500	60000	0.2755	36.9669
0.1752	3.1958	65000	0.2871	36.6628
0.1802	3.4417	70000	0.2860	36.9139
0.1864	3.6875	75000	0.2818	37.8713
0.1832	3.9334	80000	0.2804	38.1352
0.1396	4.1792	85000	0.3042	37.6950
0.1398	4.4250	90000	0.3042	37.7528
0.1482	4.6708	95000	0.2998	37.0027

ganga4364/whisper-small-v4

whisper-small-v4