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
I'm currently working on a multiclass classification problem using CatBoost with GPU acceleration. I have been trying to obtain F1 and AUC metrics during training, but I've encountered NaN values on all stages of training.
1. F1 and AUC Metrics: Can you provide guidance on how to effectively obtain F1 and AUC metrics in a multiclass setting while utilizing GPU acceleration? I noticed that using these metrics with GPU results in NaN values, and I'm seeking advice on how to handle this situation.
2. Recommended Metrics for Multiclass Classification with GPU: In the context of multiclass classification with GPU acceleration, are there specific metrics that are recommended or known to perform well? I would like to understand the best practices for selecting and monitoring metrics during training for this scenario.
I appreciate any insights or recommendations from the CatBoost team and the community. Thank you in advance for your assistance!
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hello CatBoost community!
I'm currently working on a multiclass classification problem using CatBoost with GPU acceleration. I have been trying to obtain F1 and AUC metrics during training, but I've encountered NaN values on all stages of training.
1. F1 and AUC Metrics: Can you provide guidance on how to effectively obtain F1 and AUC metrics in a multiclass setting while utilizing GPU acceleration? I noticed that using these metrics with GPU results in NaN values, and I'm seeking advice on how to handle this situation.
2. Recommended Metrics for Multiclass Classification with GPU: In the context of multiclass classification with GPU acceleration, are there specific metrics that are recommended or known to perform well? I would like to understand the best practices for selecting and monitoring metrics during training for this scenario.
I appreciate any insights or recommendations from the CatBoost team and the community. Thank you in advance for your assistance!
Beta Was this translation helpful? Give feedback.
All reactions