You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, Zhipeng
I noticed that the tpe result extractor seems do not match your tpe toolkit. The TPE toolkit worked for about 1000 times as you suggested, and save the result in 1000 different folders. It did not generate an overall log file to record every trial. I don't know if it is because I stopped the program manually by ctrl+c. Hope you can help, thanks!
The text was updated successfully, but these errors were encountered:
Hi, Zhipeng
I noticed that the tpe result extractor seems do not match your tpe toolkit. The TPE toolkit worked for about 1000 times as you suggested, and save the result in 1000 different folders. It did not generate an overall log file to record every trial. I don't know if it is because I stopped the program manually by ctrl+c. Hope you can help, thanks!
Hi, I am a little confused about your issue. Does overall log mean tune_xx.log file? It should be generated in the logs directory.
Thanks Reply
Perhaps overall log is tune_xx.log as you said, but I failed to get one log file that contains my 1000 sets of different super-parameters and the corresponding results.
I want to know if this log file generation failure is caused by my improper use of the tune_tpe.py. There are only about 1000 folders generated in ./TPE_results/zp_tune folder BTW, I manually use ctrl+C to stop tuning
Hi, Zhipeng
I noticed that the tpe result extractor seems do not match your tpe toolkit. The TPE toolkit worked for about 1000 times as you suggested, and save the result in 1000 different folders. It did not generate an overall log file to record every trial. I don't know if it is because I stopped the program manually by ctrl+c. Hope you can help, thanks!
The text was updated successfully, but these errors were encountered: