search

XuezheMax / NeuroNLP2

Deep neural models for core NLP tasks (Pytorch version)
GNU General Public License v3.0
441 stars 89 forks source link

variability in the results #40

Closed saharghannay closed 3 years ago

saharghannay commented 4 years ago

I am training a NER system, but the results change from a run to an other using the same configuration. Do you have an idea how to fix this variability please ?

XuezheMax commented 4 years ago

You can fix the random seeds for python, numpy, torch, and cuda to reduce the variance across different runs.

saharghannay commented 4 years ago

Ok thank you

Best Sahar Ghannay

Le 18 mars 2020 à 17:32, Max Ma notifications@github.com a écrit :

You can fix the random seeds for python, numpy, torch, and cuda to reduce the variance across different runs.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/XuezheMax/NeuroNLP2/issues/40#issuecomment-600733627, or unsubscribe https://github.com/notifications/unsubscribe-auth/AJ5IJQKY335E2WB27HY4WSDRIDZSPANCNFSM4LOR2BVQ.