Skip to content
This repository has been archived by the owner on Feb 12, 2022. It is now read-only.

Issues: salesforce/awd-lstm-lm

Clear current search query, filters, and sorts
55 Open 46 Closed
55 Open 46 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

The model behaves normally during training, but during prediction, the weightdrop mechanism cannot be stopped and an error is reported
#122 by zhourui-xihu was closed Sep 2, 2020
val_loss suddenly increases to a larger number(from ~5 to more than 10000)
#121 by xuuuluuu was closed Jul 23, 2020
1
AttributeError: 'LSTM' object has no attribute 'weight_hh_l0'
#119 by owaski was closed May 24, 2020
1
torch.cuda.FloatTensor
#117 by lmxhappy was closed Mar 8, 2020
Hidden state init of LSTM layers (after the first)
#116 by mourga was closed Feb 6, 2020
3
TypeError: cannot assign 'torch.cuda.FloatTensor' as parameter 'weight_hh_l0' (torch.nn.Parameter or None expected)
#114 by S-Abdelnabi was closed Jan 30, 2020
1
why is hidden layer initialized only on beginning of an epoch?
#112 by realiti4 was closed Jan 15, 2020
2
Score a test sentence
#109 by ykl7 was closed Nov 9, 2019
possible error on the neural cache model, pointer? Why use the groundtruth data?
#105 by Sunnydreamrain was closed Jun 27, 2019
1
Loading a pre-trained model with Weight Drop
#99 by dhananjaisharma10 was closed May 10, 2019
1
High Test Perplexity
#98 by Sketchizer was closed May 11, 2019
Input batch size doesn't match hidden batch size
#95 by homelifes was closed Feb 2, 2019
2
RuntimeError: expects a 2D tensor,but self is 1D
#93 by gai1995 was closed Jan 16, 2019
Is repackage_hidden(hidden) required?
#91 by felixfuu was closed Jan 2, 2019
1
KeyError: 'ax' in line `prm.data = optimizer.state[prm]['ax'].clone()
#89 by shirishr was closed Jan 6, 2019
2
KeyError: 'ax' in line prm.data = optimizer.state[prm]['ax'].clone()
#70 by wasiahmad was closed Aug 24, 2018
20
Line 80 is useless in model.py
#59 by jind11 was closed Jul 22, 2018
1
Weights sharing
#57 by enod was closed Jul 2, 2018
1
In ASGD, what do we use for parameter, is it averaged one or normal SGD one?
#54 by SongJeongHyun was closed Jul 22, 2018
1
In line 252, val_loss should be val_loss2 isn't it?
#53 by SongJeongHyun was closed Jun 13, 2018
1
Few questions about main.py
#52 by SongJeongHyun was closed Jun 16, 2018
1
How can i use Adam optimizer instead of SGD?
#50 by SongJeongHyun was closed May 29, 2018
1
Adaptive softmax question
#49 by YontiLevin was closed Jul 16, 2018
2
Triggering condition for ASGD bug
#47 by anthonywchen was closed May 17, 2018
1
Question about embedding dropout vs lockeddropout
#45 by YontiLevin was closed May 13, 2018
1
ProTip! Follow long discussions with comments:>50.