learning_rate: 1e-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_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: 153
num_epochs: 25
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
4.1433	1.0	99	0.8546	55.5692	13.8937
1.2416	2.0	198	0.5976	42.4725	10.3068
0.5530	3.0	297	0.5570	40.2693	9.3129
0.2314	4.0	396	0.6078	40.0245	8.8807
0.1007	5.0	495	0.6054	35.4957	8.2325
0.0608	6.0	594	0.6251	35.3733	8.1245
0.0368	7.0	693	0.6465	36.2301	8.2973
0.0208	8.0	792	0.6840	35.2509	8.2757
0.0110	9.0	891	0.6970	34.8837	8.0164
0.0068	10.0	990	0.6951	33.7821	7.6491
0.0029	11.0	1089	0.7220	35.3733	7.9732
0.0025	12.0	1188	0.7137	33.4149	7.5194
0.0016	13.0	1287	0.7023	33.5373	7.5411
0.0025	14.0	1386	0.7017	34.0269	7.8003
0.0012	15.0	1485	0.7127	33.6597	7.6059
0.0007	16.0	1584	0.7190	33.9045	7.6923
0.0006	17.0	1683	0.7228	33.7821	7.5843
0.0006	18.0	1782	0.7258	33.6597	7.5627
0.0005	19.0	1881	0.7285	33.6597	7.5627
0.0005	20.0	1980	0.7313	33.5373	7.5843
0.0005	21.0	2079	0.7333	33.5373	7.5627
0.0005	22.0	2178	0.7348	33.4149	7.5411

shoibo/whisper-small-santali-sanlish-1934-lr1e5

whisper-small-santali-sanlish-1934-lr1e5