Comments (3)
Thanks for your interest in our work. It usually took 8 hours to train InfoBERT with the anli_full
setting for 3 epochs given 8 GPUs. With a single GPU, I am afraid the training time is approximately 8*8=64 hours.
from infobert.
Thank you for the quick reply. This does seem like a lot and unfortunately, it might not be possible for me as a student to get hold of hardware with 8 GPUs. Do you have any suggestions on a smaller model to train or a smaller dataset which is a sample representation of ANLI?
Thanks
from infobert.
- Maybe you can try adapt the code to
roberta-base
orbert-base
to reduce the memory consumption. - You can try to run the code without adversarial training, which will save 30~60% training time.
- You can try to train your model with benign data only (SNLI + MNLI), and report its robust accuracy over ANLI test set.
from infobert.
Related Issues (5)
- How are A1,A2, A3 scores calculated from r1,r2,r3 test results? HOT 2
- Runtime Error - "Distributed package doesn't have NCCL" when running runexp HOT 2
- Training a Model from Huggingface with InfoBERT HOT 1
- RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling `cublasSgemm( handle, opa, opb, m, n, k, &alpha, a, lda, b, ldb, &beta, c, ldc)` 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 infobert.