learning_rate: 2e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
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: 20000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
0.4821	0.4	1000	0.3570	0.2268
0.4761	0.8	2000	0.3474	0.2397
0.3099	1.2	3000	0.3075	0.2026
0.3108	1.6	4000	0.2666	0.1971
0.3131	2.0	5000	0.2173	0.1531
0.1796	2.4	6000	0.2026	0.1384
0.17	2.8	7000	0.1922	0.1378
0.0995	3.2	8000	0.1792	0.1206
0.0972	3.6	9000	0.1670	0.1149
0.097	4.0	10000	0.1545	0.1096
0.0553	4.4	11000	0.1575	0.1030
0.0526	4.8	12000	0.1431	0.0890
0.0299	5.2	13000	0.1372	0.0833
0.0311	5.6	14000	0.1258	0.0780
0.0295	6.0	15000	0.1201	0.0725
0.0151	6.4	16000	0.1229	0.0742
0.0163	6.8	17000	0.1137	0.0658
0.0082	7.2	18000	0.1142	0.0639
0.0092	7.6	19000	0.1121	0.0627
0.006	8.0	20000	0.1112	0.0612

bagasshw/whisper-large-v2-javanese-openslr-v2

Whisper-Large-v2-Java-v2