learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 4
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_ratio: 0.1
training_steps: 10000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
1.1788	0.0540	500	0.9671	0.6590
0.8015	0.1081	1000	0.6977	0.5305
0.6498	0.1621	1500	0.5725	0.6670
0.5828	0.2161	2000	0.5094	0.4829
0.5226	0.2702	2500	0.4642	0.3860
0.4955	0.3242	3000	0.4341	0.3915
0.4616	0.3782	3500	0.4128	0.3540
0.4474	0.4323	4000	0.3900	0.3614
0.4387	0.4863	4500	0.3736	0.3563
0.4154	0.5403	5000	0.3606	0.3274
0.419	0.5944	5500	0.3495	0.3144
0.3799	0.6484	6000	0.3398	0.2922
0.3802	0.7024	6500	0.3290	0.3044
0.3611	0.7565	7000	0.3225	0.2823
0.3548	0.8105	7500	0.3168	0.2733
0.346	0.8645	8000	0.3105	0.2660
0.3547	0.9186	8500	0.3063	0.2708
0.3211	0.9726	9000	0.3019	0.2827
0.2718	1.0267	9500	0.2990	0.2660
0.2859	1.0807	10000	0.2980	0.2587

bagasshw/whisper-tiny-javanese-openslr-v3

Whisper-Tiny-Java-v3