Image files: ['./temp_in/zeke1.jpg', './temp_in/zeke2.jpg', './temp_in/zeke3.jpg', './temp_in/zeke4.jpg', './temp_in/zeke5.jpg', './temp_in/zeke6.jpg'] Generating 6 captions... Input captioning text: a photo of TOK, TOK he looks to be taking a selfie while sitting in the middle of the floor 0%| | 0/6 [00:00, he looks to be taking a selfie while sitting in the middle of the floor a photo of , curly man in glasses smiling in front of a beach a photo of , lacy woman wearing glasses in front of a man with curly hair a photo of , shaggy haired man in glasses looking up at something with a white wall behind him a photo of , curly man wearing glasses, white shirt and tie, stares forward a photo of , they are looking at the camera to see the man with glasses # PTI : Loaded dataset # PTI : Running training # PTI : Num examples = 6 # PTI : Num batches each epoch = 2 # PTI : Num Epochs = 250 # PTI : Instantaneous batch size per device = 4 Total train batch size (w. parallel, distributed & accumulation) = 4 # PTI : Gradient Accumulation steps = 1 # PTI : Total optimization steps = 500 0%| | 0/500 [00:00

Run time and cost