Hi
I am training the Sei model with pig data. However, during the training process, I noticed that all the loss values in the output file "selene_sdk.train_model.validation.txt" are consistently zero. Additionally, the metrics "average_precision" and "roc_auc" are reported as "NA" for all samples.
Considering your expertise in developing the SEI model, I am reaching out to seek your insights on the following questions:
- Under what circumstances could all loss values be consistently zero during training? Could this indicate any specific issues or errors in the training process?
- What could be the potential reasons behind the "NA" values for average_precision and roc_auc? Are there any common pitfalls or prerequisites that I might have overlooked?
Thanks for your help!