Hello,
One of my Spaces suddenly crashed without any useful error messages. The Docker version of Space works just fine on my local machine. I suspect this is related to the new persistent storage model, as the space crashes right after it finishes downloading the weights.
Any help or suggestions are appreciated.
Container logs:
===== Application Startup at 2023-08-11 14:13:25 =====
Downloading (…)solve/main/vocab.txt: 0%| | 0.00/232k [00:00<?, ?B/s]
Downloading (…)solve/main/vocab.txt: 100%|██████████| 232k/232k [00:00<00:00, 54.0MB/s]
Downloading (…)okenizer_config.json: 0%| | 0.00/28.0 [00:00<?, ?B/s]
Downloading (…)okenizer_config.json: 100%|██████████| 28.0/28.0 [00:00<00:00, 194kB/s]
Downloading (…)lve/main/config.json: 0%| | 0.00/570 [00:00<?, ?B/s]
Downloading (…)lve/main/config.json: 100%|██████████| 570/570 [00:00<00:00, 3.96MB/s]
0%| | 0.00/1.89G [00:00<?, ?B/s]
0%| | 4.01M/1.89G [00:00<01:14, 27.0MB/s]
[MESSAGE TRUNCATED]
100%|██████████| 1.89G/1.89G [00:09<00:00, 219MB/s]
Downloading pytorch_model.bin: 0%| | 0.00/440M [00:00<?, ?B/s]
Downloading pytorch_model.bin: 2%|▏ | 10.5M/440M [00:00<00:10, 40.5MB/s]
[MESSAGE TRUNCATED]
Downloading pytorch_model.bin: 100%|█████████▉| 5.28G/5.30G [01:59<00:00, 59.4MB/s]
Downloading pytorch_model.bin: 100%|██████████| 5.30G/5.30G [01:59<00:00, 44.3MB/s]
. It got resolved automatically, whatever it was.