optimizer: {'name': 'AdamW', 'weight_decay': 0.01, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'ExponentialDecay', 'config': {'initial_learning_rate': 0.002, 'decay_steps': 10000, 'decay_rate': 0.01, 'staircase': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
training_precision: float32

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
1.1049	0.6128	0.7422	0.7517	0
0.7149	0.7564	0.6376	0.7821	1
0.6080	0.7945	0.6947	0.7745	2
0.5376	0.8160	0.5589	0.8134	3
0.4977	0.8279	0.5458	0.8162	4
0.4564	0.8407	0.4799	0.8441	5
0.4271	0.8557	0.4765	0.8413	6
0.3957	0.8619	0.4790	0.8453	7
0.3701	0.8741	0.5376	0.8329	8
0.3425	0.8829	0.4359	0.8619	9
0.3192	0.8892	0.4475	0.8585	10
0.2972	0.8967	0.4143	0.8712	11
0.2691	0.9080	0.4819	0.8498	12
0.2445	0.9144	0.4543	0.8563	13
0.2261	0.9220	0.4221	0.8689	14
0.2127	0.9251	0.5076	0.8540	15
0.1914	0.9341	0.5148	0.8512	16