Closed spencermyoung513 closed 4 months ago
Got some encouraging results with the following training settings:
epochs: 2000
batch_size: 32
lr: 1e-3
weight_decay: 1e-5
optimizer: AdamW
lr_scheduler: CosineAnnealingLR
I also trained each network 10 times. Crossing my fingers that we've found some stability.
In our brief experiments training neural networks with the Double Poisson NLL, we have observed a large variance in the resultant model's metrics (primarily MSE). This could be due to a variety of factors. The goal is to design a training process with the Double Poisson NLL that consistently outputs good models (with low variance in terms of model MSE across random initializations).
Areas to tinker with: