Parameters: { silent } might not be used

Questions
#1

I used autotvm to tune my model by XGBTuner. During tunning, I can see this WARNING:

[Task  1/29]  Current/Best:  885.44/ 885.44 GFLOPS | Progress: (48/2000) | 42.43 s[03:52:07] WARNING: /workspace/src/learner.cc:480: 
Parameters: { silent } might not be used.

  This may not be accurate due to some parameters are only used in language bindings but
  passed down to XGBoost core.  Or some parameters are not used but slip through this
  verification. Please open an issue if you find above cases.

What does it mean? Will it harm the inference performance ?

#2

I’m facing similar issue.

#3

It is due to an update from the xgboost side that deprecates the silent parameter, we should change to verbosity=0

#4
1 Like
#5

I change to verbosity=0 ,but but there is the warning

Parameters: { silent } might not be used.

  This may not be accurate due to some parameters are only used in language bindings but
  passed down to XGBoost core.  Or some parameters are not used but slip through this
  verification. Please open an issue if you find above cases.

tvm0.7 dev
windows xgboost version :1.1.0

#6

You might need to check the path of imported tvm

import tvm
print(tvm.__file__)

Changing verbosity=0 worked for me.

#7

it’s working. I don’t change key form '‘silent’ to ‘verbosity’. :joy: