Comments (2)
Hi, I'm trying to reproduce the result of XSUM from scratch too, using recommended parameters in README. But I cannot reproduce the ROUGE score, which is much lower than the score reported in the paper. Any suggestions? @qiweizhen , thank you!
from prophetnet.
Diffusion models w/o pre-training often require more training steps. If you want to reproduce the results from scratch, you need to set the --lr_anneal_steps
to more (e.g. Xsum 400k steps). We hope this suggestion can help you.
We have noticed that our description of training from scratch in README
have caused some misunderstandings, and we will update and correct them in the next version. Thank you for your feedback.
from prophetnet.
Related Issues (20)
- Can use_fp16 be used?
- Why is the GENIE result in AR-diffusion very different from the original paper? Also, you come from a team. HOT 1
- Character level
- Can't Find Pretrained Checkpoint of Prophetnet: HOT 1
- Unable to load the GENIE model HOT 3
- The datasets have no dev set? HOT 1
- Options Employed for Training or Inference on the CNN/DM Dataset HOT 1
- It seems that the core code of CRITIC, particularly the part involving Google API search, is not implemented HOT 4
- Missing key documents for AR-Diffusion HOT 1
- where is "mbr_select.py" in AR-Diffusion HOT 1
- Unable to run Genie_Finetune.py HOT 1
- “load_fairseq” not found in "AR-Diffusion/data_utils" HOT 3
- Question for GENIE Finetuning, how to specify epochs for training/finetuning? HOT 1
- “load_fairseq” not found in "AR-Diffusion/data_utils" HOT 1
- [AR-Diffusion] predict_xstart vs predict_x_start HOT 3
- AR-Diffusion data.name and exp.name HOT 2
- Request the execution code of llama2
- AR-diffusion: where the code for algorithm 1 is located? HOT 4
- (AR-Diffusion) RuntimeError: Error(s) in loading state_dict for CrossAttention_Diffusion_LM HOT 3
- what is the need for `num_samples` parameter in inference? 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 prophetnet.