Jetson Xavier doesnt use GPU while training YOLOV5 custom data

AutoAnchor: 4.35 anchors/target, 1.000 Best Possible Recall (BPR). Current anchors are a good fit to dataset ✅
Image sizes 416 train, 416 val
Using 4 dataloader workers
Logging results to runs/train/yolov5s_results12
Starting training for 40 epochs…

 Epoch   gpu_mem       box       obj       cls    labels  img_size
  0/39        0G   0.09895   0.01928   0.02357        37       416:  16%|

also while checking torch.is_available().cuda returns FALSE

Anyone to help

Hello, this forum is dedicated to discussions related to using the sanitizer tools and API.
Questions related to CUDA can be raised at CUDA - NVIDIA Developer Forums