learning_rate: 5e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 50
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer Score
84.9149	3.6893	100	2.9324	3.8749
39.5513	7.3991	200	2.6633	2.6427
28.5436	11.1088	300	2.7566	3.0925
20.9713	14.7982	400	2.8737	3.2221
15.2719	18.5079	500	2.9953	2.9620
11.4351	22.2177	600	3.1084	3.0657
8.6091	25.9070	700	3.1823	3.1642
6.4907	29.6168	800	3.2530	3.0930
5.0524	33.3265	900	3.3025	3.1223
4.0674	37.0363	1000	3.3509	3.1089
3.3508	40.7256	1100	3.3843	3.1288
2.8752	44.4354	1200	3.4132	3.1570
2.5338	48.1451	1300	3.4281	3.2039

faluradu/git-base-appliances

git-base-appliances