Training CNEP with different LR & Warmup
Setup:
1. Sentence-Transformer pretrained as encoder for MIMIC-III Clinical Notes,
2. LSTMCNN + Dense Layer pretrained on MIMIC-III/Readmission (w/o Clinical Notes) as encoder for Events and charts data
Created on December 12|Last edited on December 12
Comment
Content
Loss and Training
Validation
Run set
0
Images
Sample of Logits per Events Data/Train Dataset after 45 epochs
Sample of Logits per Events Data/Eval Dataset after 45 epochs
Logits per Events Data/Full Evaluation Dataset after 45 epochs
Add a comment