-
Notifications
You must be signed in to change notification settings - Fork 487
finetune & pointer bugs? #26
Comments
Hey @aykutfirat, We've replicated the same issue you're seeing in terms of the initial training performance for ASGD based WT2, in our case using QRNN as it's faster to test. This is as I patched our changes for the Adam based model we used for WT-103, PTBC, and enwik8 over the top of AWD-LSTM-LM but failed to do full testing for regression. We're hunting down the issue now, initially to fix the standard training and then later to fix the finetune and pointer steps. |
It is probably a related issue, so I thought I would report it here. When running
|
python finetune.py --epochs 750 --data data/wikitext-2 --save WT2.pt --dropouth 0.2 --seed 1882
python pointer.py --save WT2.pt --lambdasm 0.1279 --theta 0.662 --window 3785 --bptt 2000 --data data/wikitext-2
Traceback (most recent call last):
File "finetune.py", line 183, in
stored_loss = evaluate(val_data)
File "finetune.py", line 108, in evaluate
model.eval()
Looks like model loading & more needs to be modified.
Also, I no longer get the reported ppls in main. LSTM gets stuck around 80s and QRNN around 90s.
The text was updated successfully, but these errors were encountered: