learning_rate: 0.0003
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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_ratio: 0.1
num_epochs: 100
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
14.9517	6.6667	20	5.1569	1.0
4.5284	13.3333	40	3.6413	1.0
3.571	20.0	60	3.6094	1.0
3.2872	26.6667	80	3.5732	1.0
3.1311	33.3333	100	3.4355	1.0
2.9955	40.0	120	3.3223	1.0
2.9259	46.6667	140	3.3184	1.0
2.8683	53.3333	160	3.2794	1.0
2.7513	60.0	180	3.3916	1.0
2.5434	66.6667	200	3.3479	1.0
2.2682	73.3333	220	3.3794	1.0
2.0945	80.0	240	3.3626	1.0
1.9457	86.6667	260	3.3331	1.0
1.8294	93.3333	280	3.3506	1.0
1.7562	100.0	300	3.3678	1.0

dennohpeter/wav2vec2-xls-r-300m-100e-lg-asr

wav2vec2-xls-r-300m-100e-lg-asr