optimizer: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 1200, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
training_precision: mixed_float16

Train Loss	Train Accuracy	Train Top-3-accuracy	Validation Loss	Validation Accuracy	Validation Top-3-accuracy	Epoch
3.6575	0.0902	0.1945	3.1772	0.2028	0.3980	0
2.5870	0.3473	0.6048	2.3845	0.3717	0.6208	1
1.8813	0.5553	0.7895	2.0262	0.4431	0.7196	2
1.4326	0.6815	0.8754	1.8856	0.4793	0.7384	3
1.0572	0.7989	0.9439	1.6570	0.5369	0.7960	4
0.7740	0.8838	0.9749	1.6103	0.5557	0.7960	5
0.5593	0.9417	0.9900	1.5303	0.5695	0.8173	6
0.4151	0.9709	0.9975	1.4939	0.5795	0.8185	7
0.3176	0.9884	0.9978	1.4553	0.5832	0.8248	8
0.2582	0.9950	0.9991	1.4500	0.6020	0.8248	9
0.2222	0.9978	0.9994	1.4315	0.6108	0.8310	10
0.2020	0.9984	0.9997	1.4297	0.6195	0.8298	11