learning_rate: 0.0004
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use 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_steps: 132
num_epochs: 100
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
4.9501	6.6667	200	3.0654	1.0
2.9958	13.3333	400	2.8175	1.0
2.5806	20.0	600	2.2179	1.0
1.4475	26.6667	800	1.4198	0.7254
0.6646	33.3333	1000	1.5241	0.6384
0.3545	40.0	1200	1.5196	0.5915
0.2218	46.6667	1400	1.6719	0.5737
0.1683	53.3333	1600	1.8144	0.5737
0.1259	60.0	1800	1.8164	0.5603
0.09	66.6667	2000	2.0002	0.5424
0.0888	73.3333	2200	2.0032	0.5536
0.0589	80.0	2400	2.0328	0.5469
0.0471	86.6667	2600	2.0949	0.5603
0.0392	93.3333	2800	2.2458	0.5469
0.0317	100.0	3000	2.1813	0.5491

susmitabhatt/xlsr-nm-nose

xlsr-nm-nose