Any ideas what this issue could mean and how to solve it?
I'm getting it anytime I try to create predictors from deep tables models
Error code below
[2024-06-18 12:42:22] FAILURE - cannot pickle 'weakref' object
Traceback (most recent call last):
File "/app/src/task/ai_job.py", line 159, in run_job
getattr(AIService(), task_method)(r.updater)
File "/app/src/services/ai.py", line 431, in train_predict
inducer_mb = ObjectService.save_inducer(inducer, AIPath.inducer(updater.obj))
File "/app/src/services/object.py", line 201, in save_inducer
return cls._write(inducer, resolver(path))
File "/app/src/services/object.py", line 34, in _write
pickle.dump(data, fd)
TypeError: cannot pickle 'weakref' object
[2024-06-18 12:42:21] PROGRESS - storing result
[2024-06-18 12:42:21] Peak memory usage: 4189MB
[2024-06-18 12:41:36] WARNING - FutureWarning: The `needs_threshold` and `needs_proba` parameter are deprecated in version 1.4 and will be removed in 1.6. You can either let `response_method` be `None` or set it to `predict` to preserve the same behaviour.
[2024-06-18 12:41:33] PROGRESS - fitting model
[2024-06-18 12:41:31] PROGRESS - retrieving data
[2024-06-18 12:41:31] Baseline memory usage: 186MB
[2024-06-18 12:41:31] STARTED
