The system configuration of this work

[lemonci]

I am using a GeForce 3070 on Ubuntu 20.04, as there is no cuda 10.1 for Ubuntu 20.04. I have to install the following version of pytorch instead of the ones listed in your yaml file:

` package | build
---------------------------|-----------------
_pytorch_select-0.2 | gpu_0 2 KB
cudnn-7.6.5 | cuda10.1_0 179.9 MB
pytorch-1.4.0 |cuda101py37h02f0884_0 167.4 MB
------------------------------------------------------------
Total: 347.4 MB

The following NEW packages will be INSTALLED:

_pytorch_select pkgs/main/linux-64::_pytorch_select-0.2-gpu_0
cudnn pkgs/main/linux-64::cudnn-7.6.5-cuda10.1_0
pytorch pkgs/main/linux-64::pytorch-1.4.0-cuda101py37h02f0884_0
When trying to runevaluate_generator.py,` I received multiple warnings like:

-- WARNING: 63 PYTHON workers have been started. This could be a result of using a large number of actors, or it could be a consequence of using nested tasks (see https://github.com/ray-project/ray/issues/3644) for some a discussion of workarounds.

Then tqdm progress bar doesn't move at all:
Loaded generator network and optimizer from path: downloads/checkpoints/fit2form.pth <learning.finger_generator.TrainedGNFingerGenerator object at 0x7fbe0018e590> fit2form: 0%| | 0/40 [00:00<?, ?it/s]

And after running nvidia-smi:

`Wed Aug 28 05:50:01 2024
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 470.256.02 Driver Version: 470.256.02 CUDA Version: 11.4 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 NVIDIA GeForce ... On | 00000000:01:00.0 On | N/A |
| 30% 46C P2 41W / 220W | 4341MiB / 7982MiB | 5% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 1195 G /usr/lib/xorg/Xorg 360MiB |
| 0 N/A N/A 1715 G /usr/bin/gnome-shell 112MiB |
| 0 N/A N/A 3524 G /usr/lib/firefox/firefox 627MiB |
| 0 N/A N/A 22385 G ...--variations-seed-version 64MiB |
| 0 N/A N/A 58185 C ...--name evaluation_results 3171MiB |
+-----------------------------------------------------------------------------+
`

Please suggest if you used a more powerful GPU for training (as not mentioned in the paper), or I have to run the code on Ubuntu 18 with CUDA 10 with your configurations. Thanks.