Pytorch CUDA P100 GPU Incompatibility

## 🐛 Bug

The model fails to train on GPU due to a CUDA capability mismatch. The installed version of PyTorch requires CUDA capability sm_70 or higher, but the available GPU (Tesla P100-PCIE-16GB) only supports sm_60. Here is traceback:

```
/usr/local/lib/python3.12/dist-packages/torch/cuda/__init__.py:435: UserWarning:
Found GPU0 Tesla P100-PCIE-16GB which is of cuda capability 6.0.
Minimum and Maximum cuda capability supported by this version of PyTorch is
(7.0) - (12.0)

queued_call()
/usr/local/lib/python3.12/dist-packages/torch/cuda/__init__.py:435: UserWarning:
Please install PyTorch with a following CUDA
configurations: 12.6 following instructions at
https://pytorch.org/get-started/locally/

queued_call()
/usr/local/lib/python3.12/dist-packages/torch/cuda/__init__.py:435: UserWarning:
Tesla P100-PCIE-16GB with CUDA capability sm_60 is not compatible with the current PyTorch installation.
The current PyTorch install supports CUDA capabilities sm_70 sm_75 sm_80 sm_86 sm_90 sm_100 sm_120.
If you want to use the Tesla P100-PCIE-16GB GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/

queued_call()
```

### To Reproduce

Use P100 GPU on Kaggle, move Pytorch neural network model to GPU and start training loop.

### Expected behavior

Successful forward training pass without errors.

### Additional context

This was the error given:

```
AcceleratorError: CUDA error: no kernel image is available for execution on the device
Search for `cudaErrorNoKernelImageForDevice' in https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__TYPES.html for more information.
```

Code worked fine for me a few weeks ago, but I'm guessing a change in the Docker environment broke something.

Reproduziere die Trainingsschleife auf einer Kaggle Tesla P100 und prüfe die PyTorch- und CUDA-Versionen der Docker-Umgebung. Vergleiche die installierte Konfiguration mit der unterstützten sm_60-Fähigkeit und den PyTorch-Hinweisen zu CUDA 12.6; als erledigt gilt dies, wenn das Image entweder einen erfolgreichen Forward-Trainingsdurchlauf auf der P100 unterstützt oder die Inkompatibilität und die erforderliche Umgebung eindeutig dokumentiert.

Vom Indexierungsmodell aus dem Issue-Text verfasst.