runtime error

Exit code: 1. Reason: . Please use `torch.amp.custom_fwd(args..., device_type='cuda')` instead. def forward(ctx, input, target): /usr/local/lib/python3.10/site-packages/onmt/modules/sparse_losses.py:37: FutureWarning: `torch.cuda.amp.custom_bwd(args...)` is deprecated. Please use `torch.amp.custom_bwd(args..., device_type='cuda')` instead. def backward(ctx, grad_output): IDEA-OCSR-v1.0.0.pth: 0%| | 0.00/1.13G [00:00<?, ?B/s] IDEA-OCSR-v1.0.0.pth: 0%| | 0.00/1.13G [00:01<?, ?B/s] IDEA-OCSR-v1.0.0.pth: 0%| | 94.6k/1.13G [00:02<3:26:56, 91.4kB/s] IDEA-OCSR-v1.0.0.pth: 0%| | 94.6k/1.13G [00:20<3:26:56, 91.4kB/s] IDEA-OCSR-v1.0.0.pth: 6%|▋ | 72.9M/1.13G [00:49<11:40, 1.51MB/s]  IDEA-OCSR-v1.0.0.pth: 19%|█▉ | 219M/1.13G [00:53<02:53, 5.27MB/s]  IDEA-OCSR-v1.0.0.pth: 80%|████████ | 911M/1.13G [00:54<00:07, 30.5MB/s] IDEA-OCSR-v1.0.0.pth: 100%|██████████| 1.13G/1.13G [00:54<00:00, 20.7MB/s] /usr/local/lib/python3.10/site-packages/torch/functional.py:505: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /pytorch/aten/src/ATen/native/TensorShape.cpp:4381.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] ******************************************** * Trying to transpile functions from Python -> JS for performance * (1/1) <lambda>: ✅ ******************************************** GRADIO_HOT_RELOAD: Using 'iface' for demo name * Running on local URL: http://0.0.0.0:7860, with SSR ⚡ (experimental, to disable set `ssr_mode=False` in `launch()`) Traceback (most recent call last): File "/app/app.py", line 66, in <module> iface.launch() File "/usr/local/lib/python3.10/site-packages/gradio/blocks.py", line 2848, in launch raise ValueError( ValueError: When localhost is not accessible, a shareable link must be created. Please set share=True or check your proxy settings to allow access to localhost.

Container logs: