Question about text_to_image

[mahmoodn]

When I run the text_to_image command

python3 main.py --dataset "coco-1024" --dataset-path coco2014 \
   --profile stable-diffusion-xl-pytorch --model-path ./model/stable_diffusion_fp32 \
   --dtype fp32 --device cuda --scenario Offline

I see a bunch of output lines like this:

Loading pipeline components...: 100%|██████████| 7/7 [00:29<00:00,  4.21s/it]
/scratch/mahmood/inference/text_to_image/coco.py:58: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.
  torch.load(f"{data_path}/latents/latents.pt")

100%|██████████| 20/20 [00:18<00:00,  1.10it/s]
100%|██████████| 20/20 [00:12<00:00,  1.54it/s]
...

I have counted the number of progress bars in 24 hours on an A100 GPU and it was about 5000 lines. The question is are these progress bars some kind of creating chunks before the real execution or those or the actual outputs from the inference execution?