dropreg R-Drop issues - Githubissues

dropreg / R-Drop

867 stars 107 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Clarification on Using Concatenated Input for R-Drop Training

#33 xyb314 closed 7 months ago
1
How to use the data parallel in r-drop.

#32 xinxinxing closed 1 year ago
1
Question of the proof

#31 SYSUykLin closed 2 years ago
1
Some question about reproducing GLUE

#30 wpwpwpyo opened 2 years ago
0
kl loss in ViT example supposed to be divided by 2?

#29 sieu-n closed 2 years ago
1
How the `warmup steps` affects the performance?

#28 Doragd closed 2 years ago
2
Can I use R-Drop in Semantic Search?

#27 ralgond closed 2 years ago
1
Update README.md

#26 double22a closed 2 years ago
0
Can not reproduce following the hyperparameter in the paper for finefuning ViT on Cifar100

#25 NamlessM closed 2 years ago
4
About the implementation in transformers, where the reduction in ce_loss uses the mean (by default), while KL uses the reduction is sum ?

#24 XiaoqingNLP closed 2 years ago
1
can not reproduce the results following the hyparameters in the paper

#23 leoozy closed 2 years ago
1
error: argument --task: invalid choice: 'rdrop_translation'

#22 tairan-w closed 2 years ago
1
difference between R-Drop and SimCse + Smart

#21 cuixuage closed 2 years ago
1
Can mseloss replace KL divergence？

#20 18335100284 closed 2 years ago
1
Training configuration for the WMT14 EnDe dataset?

#19 frankang closed 2 years ago
5
Where is R-Drop code in R-Drop/huggingface_transformer_src/bert_rdrop/run_glue.py?

#18 zhenshiqi1996 closed 2 years ago
6
JS divergence in the research paper?

#17 sieu-n closed 2 years ago
1
unable to reproduce results on GLUE

#16 1024er closed 2 years ago
2
pip install --editable .报错

#15 Shiwen-Ni closed 2 years ago
1
Unable to preprocess data for summarization

#14 samiksome92 closed 2 years ago
2
What's Wrong with my TensorFlow (1.14 or 1.15) implementation?

#13 guotong1988 closed 2 years ago
2
R-drop makes my model broken.

#12 MayDomine closed 2 years ago
9
Readme File for RoBerta example.

#11 ShreyPandit closed 3 years ago
1
A simple way to double the impact of R-Drop

#10 guotong1988 closed 3 years ago
3
CUDA error: CUBLAS_STATUS_EXECUTION_FAILED

#9 paul-chelarescu closed 3 years ago
2
Summarization task fails with 'Trying to backward through the graph a second time'

#8 paul-chelarescu closed 3 years ago
2
what the dropout should be set when we predict or test?

#7 hitwangshuai closed 3 years ago
2
Inconsistency for KL loss and CE loss hyper-parameters and baselines results in GLUE

#6 zhangzhenyu13 closed 3 years ago
5
Will KLD loss degrease very fast?

#5 snsun closed 2 years ago
9
Fairseq tasks install work?

#4 kungfu-eric closed 3 years ago
1
Why you use (p, q_tec) and (q, p_tec) rather than (p, q) and (q, p) to compute kl-loss?

#3 JaheimLee closed 3 years ago
0
What are the core code lines of R-Drop? Thank you very much.

#2 guotong1988 closed 3 years ago
1
What are the core code lines of R-Drop? Thank you very much.

#1 guotong1988 closed 3 years ago
0