Hi, I have a model and I can perfectly build and fit it on my machine.
The problem is that when I run it on docker with many sample > 200 I have a weird error:
Sampling: 90% (2700/3000)
Sampling: 93% (2800/3000)
Sampling: 97% (2900/3000)INFO:httpstan:Operationoperations/rgc3xdv4
finished.
CRITICAL:httpstan:Operationoperations/odhmza7x
cancelled before finishing.
ERROR:asyncio:Exception in callback handle_create_fit.._services_call_done({‘done’: True, ‘metadata’: {‘fit’: {‘name’: ‘models/3bd4r…fits/odhmza7x’}, ‘progress’: ‘Iteration: 1…] (Sampling)’}, ‘name’: ‘operations/odhmza7x’})(>) at /usr/local/lib/python3.9/site-packages/httpstan/views.py:367
handle: <Handle handle_create_fit.._services_call_done({‘done’: True, ‘metadata’: {‘fit’: {‘name’: ‘models/3bd4r…fits/odhmza7x’}, ‘progress’: ‘Iteration: 1…] (Sampling)’}, ‘name’: ‘operations/odhmza7x’})(>) at /usr/local/lib/python3.9/site-packages/httpstan/views.py:367>
Traceback (most recent call last):
File “/usr/local/lib/python3.9/asyncio/runners.py”, line 44, in run
return loop.run_until_complete(main)
File “/usr/local/lib/python3.9/asyncio/base_events.py”, line 642, in run_until_complete
return future.result()
File “/usr/local/lib/python3.9/site-packages/stan/model.py”, line 198, in go
resp = await client.get(f"/{operation[‘name’]}“)
File “/usr/local/lib/python3.9/site-packages/stan/common.py”, line 46, in get
async with self.session.get(f”{self.base_url}{path}") as resp:
File “/usr/local/lib/python3.9/site-packages/aiohttp/client.py”, line 1117, in aenter
self._resp = await self._coro
File “/usr/local/lib/python3.9/site-packages/aiohttp/client.py”, line 544, in _request
await resp.start(conn)
File “/usr/local/lib/python3.9/site-packages/aiohttp/client_reqrep.py”, line 905, in start
self._continue = None
File “/usr/local/lib/python3.9/site-packages/aiohttp/helpers.py”, line 656, in exit
raise asyncio.TimeoutError from None
asyncio.exceptions.TimeoutErrorDuring handling of the above exception, another exception occurred:
Traceback (most recent call last):
File “/usr/local/lib/python3.9/site-packages/httpstan/services_stub.py”, line 145, in call
await asyncio.sleep(0.001)
File “/usr/local/lib/python3.9/asyncio/tasks.py”, line 655, in sleep
return await future
asyncio.exceptions.CancelledErrorDuring handling of the above exception, another exception occurred:
Traceback (most recent call last):
File “/usr/local/lib/python3.9/asyncio/events.py”, line 80, in _run
self._context.run(self._callback, *self._args)
File “/usr/local/lib/python3.9/site-packages/httpstan/views.py”, line 380, in _services_call_done
exc = future.exception()
asyncio.exceptions.CancelledError
Traceback (most recent call last):
File “//main.py”, line 174, in
main()
File “//main.py”, line 109, in main
latent_model.fit_model(
File “/src/models/latent.py”, line 100, in fit_model
self.fit = self.posterior.sample(num_chains=num_chains, num_samples=samples)
File “/usr/local/lib/python3.9/site-packages/stan/model.py”, line 84, in sample
return self.hmc_nuts_diag_e_adapt(num_chains=num_chains, **kwargs)
File “/usr/local/lib/python3.9/site-packages/stan/model.py”, line 103, in hmc_nuts_diag_e_adapt
return self._create_fit(function=function, num_chains=num_chains, **kwargs)
File “/usr/local/lib/python3.9/site-packages/stan/model.py”, line 306, in _create_fit
return asyncio.run(go())
File “/usr/local/lib/python3.9/asyncio/runners.py”, line 44, in run
return loop.run_until_complete(main)
File “/usr/local/lib/python3.9/asyncio/base_events.py”, line 642, in run_until_complete
return future.result()
File “/usr/local/lib/python3.9/site-packages/stan/model.py”, line 198, in go
resp = await client.get(f"/{operation[‘name’]}“)
File “/usr/local/lib/python3.9/site-packages/stan/common.py”, line 46, in get
async with self.session.get(f”{self.base_url}{path}") as resp:
File “/usr/local/lib/python3.9/site-packages/aiohttp/client.py”, line 1117, in aenter
self._resp = await self._coro
File “/usr/local/lib/python3.9/site-packages/aiohttp/client.py”, line 544, in _request
await resp.start(conn)
File “/usr/local/lib/python3.9/site-packages/aiohttp/client_reqrep.py”, line 905, in start
self._continue = None
File “/usr/local/lib/python3.9/site-packages/aiohttp/helpers.py”, line 656, in exit
raise asyncio.TimeoutError from None
asyncio.exceptions.TimeoutError
When the sample size is smaller (100) it runs with no error.
What can be the cause?