Comments (6)
It depends on what your goal is using diffusion model for MT tasks. Follow-up works are not exactly the same with DiffuSeq. SeqDiffuSeq is based on encoder-decoder architecture, while RDM is based on discrete text diffusion. This work also involves pre-trained MLMs. If you're aiming the performance, you could refer to the SOTA model.
from diffuseq.
Hi,
Maybe you can try our updated version 2, which is 4x faster on training and 800x faster on sampling on QQP datasets. [We update the information of v2 in README.md]
from diffuseq.
Hi,
You can have a try. But different hyper-parameters may lead to different results, including bsz, steps, dim, seq_len, and tokenizers. Currently many follow-up works achieve better MT performance and you can refer to their codebase, too.
from diffuseq.
Yeah makes sense, thanks! Are you referring to works like SeqDiffuSeq which builds on DiffuSeq directly?
from diffuseq.
@summmeer thanks, this is very helpful! in the paper DiNoiSer, the authors claim to have surpassed DiffuSeq's performance on the WMT14 EN->DE task, so I wanted to do a similar comparison between DiffuSeq and DiNoiSer on the IWSLT14 task, but DiffuSeq takes a long time to train.
Even with the QQP task reported in the paper, I tried training it to replicate the results and on 4 A100 GPUs it took 6.5 days to train (WandB overview), so do you think there is additional distributed training code required to train DiffuSeq more efficiently?
Sorry for the trivial question, your replies are really helpful, thanks!
from diffuseq.
I will, thanks a lot!
from diffuseq.
Related Issues (20)
- BERT parameter
- Try to train the model with another dataset, but get so many [UNK] token. HOT 1
- a few questions about the 'MBR' decoding strategy. HOT 2
- Version of many packages
- Incorrect self-BLEU Computation
- a question about --local_rank
- Could not find a version that satisfies the requirement torch==1.9.0+cu111
- i face some promble Dataset(2) in "text_datasets.py" HOT 1
- If there is any rule to modify the parameters HOT 1
- A question about the loss in V2
- Implementation of using soft absorbing state in the forward process in training. HOT 1
- ddim sampling HOT 2
- DDPM HOT 3
- train
- Where is CommonsenseConversation/test.jsonl ? When I run train. sh and then run run_decode_solver. sh or run_decode. sh, I always can't find test.jsonl HOT 2
- 'grad_norm' is NaN HOT 3
- Understanding tT_loss HOT 2
- questions on source data HOT 1
- Text simplification dataset HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from diffuseq.