learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 200
num_epochs: 15
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
0.8495	1.0	268	0.6232	0.3815	0.1517
0.4653	2.0	536	0.5281	0.3612	0.1496
0.3145	3.0	804	0.5185	0.3169	0.1267
0.1865	4.0	1072	0.5390	0.3227	0.1308
0.1128	5.0	1340	0.5657	0.3236	0.1284
0.0654	6.0	1608	0.6066	0.3150	0.1245
0.0276	7.0	1876	0.6278	0.3210	0.1302
0.0194	8.0	2144	0.6498	0.3197	0.1253
0.0078	9.0	2412	0.6749	0.3240	0.1292
0.0052	10.0	2680	0.6909	0.3154	0.1271
0.0024	11.0	2948	0.7041	0.3107	0.1232
0.0028	12.0	3216	0.7126	0.3165	0.1258
0.0016	13.0	3484	0.7215	0.3142	0.1255
0.0012	14.0	3752	0.7256	0.3120	0.1241
0.0011	15.0	4020	0.7279	0.3118	0.1242

smutuvi/ndizi-whisper-small-optimized_1

ndizi-whisper-small-optimized