learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 4
seed: 42
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: 20
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Bleu
2.5261	0.2633	500	1.1977	0.4359
1.1455	0.5266	1000	0.7789	0.4657
0.8398	0.7899	1500	0.6254	0.4128
0.7001	1.0532	2000	0.5315	0.7362
0.5917	1.3165	2500	0.4880	0.7590
0.5684	1.5798	3000	0.4533	0.7101
0.5297	1.8431	3500	0.4382	0.7719
0.4913	2.1064	4000	0.4129	0.7696
0.4706	2.3697	4500	0.4068	0.7719
0.4529	2.6330	5000	0.3933	0.7580
0.4318	2.8963	5500	0.3859	0.7709
0.4242	3.1596	6000	0.3753	0.7523

Humphery7/build_your_circuit

build_your_circuit