learning_rate: 0.001
train_batch_size: 2
eval_batch_size: 8
seed: 42
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: 100
num_epochs: 5
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
6.573	0.2584	100	1.0665	0.6766
0.9412	0.5168	200	0.8605	0.5970
0.7877	0.7752	300	0.7948	0.5750
1.0771	1.0336	400	0.7438	0.5479
0.718	1.2920	500	0.7305	0.5346
0.6581	1.5504	600	0.7471	0.5057
0.9717	1.8088	700	0.7074	0.4965
0.6783	2.0672	800	0.6970	0.5007
0.6062	2.3256	900	0.6747	0.4731
0.8629	2.5840	1000	0.6719	0.4912
0.6127	2.8424	1100	0.6501	0.4662
0.5476	3.1008	1200	0.6517	0.4508
0.5371	3.3592	1300	0.6532	0.4826
0.5478	3.6176	1400	0.6404	0.4498
0.5208	3.8760	1500	0.6335	0.4469
0.7972	4.1344	1600	0.6376	0.4379
0.4907	4.3928	1700	0.6365	0.4362
0.4927	4.6512	1800	0.6320	0.4330
0.8188	4.9096	1900	0.6250	0.4330

robertp408/wav2vec2-large-mms-1b-aft-el-CY

wav2vec2-large-mms-1b-aft-el-CY