optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 0.0005, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0005, 'decay_steps': 2554800, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'passive_serialization': True}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.99, 'epsilon': 0.2, 'amsgrad': False, 'weight_decay_rate': 0.01}
training_precision: float32

Train Loss	Train Rouge	Validation Loss	Validation Rouge	Epoch
1.5411	0.4201	1.0250	0.4297	0
1.1803	0.4674	0.9795	0.4437	1
1.1391	0.4801	0.9588	0.4523	2
1.1168	0.4869	0.9395	0.4590	3
1.1038	0.4912	0.9318	0.4613	4
1.0971	0.4934	0.9305	0.4611	5
1.0949	0.4945	0.9287	0.4621	6
1.0965	0.4948	0.9313	0.4605	7
1.1002	0.4943	0.9385	0.4581	8

Beeseey/gpt_image_clef1

gpt_image_clef1