Comments (2)
We checked the parameters in config.json, learning_rate should be set to 2e-4.
More detailed model parameters can be found in training_args.bin in huggingface.co/Langboat/ReGPT-125M-200G model file.
Thanks for pointing this out!
from mengzi-retrieval-lm.
Thanks for your reply. I will try again.
from mengzi-retrieval-lm.
Related Issues (20)
- Customize knowledge db HOT 3
- api.py HOT 1
- Approximate Training Time HOT 11
- Question For Training Dataset HOT 2
- 200G retrieval library HOT 1
- Need more ressources? :) HOT 1
- Re_gptForCausalLM were not initialized from the model checkpoint at EleutherAI/gpt-neo-125M
- Eval_loss NaN with train/train.py
- Prepare_load
- Error while training HOT 1
- Unable to reproduce PPL for GPT-Neo-125M using lm-eval HOT 1
- trainer训练很慢 HOT 1
- prepare_load.py dosen't filter the len(input_ids) < chunk_size data like dataset.py
- About the compute resources HOT 2
- Any Web Demo to have a look at it?
- Prompt for Result
- Langboat/ReGPT-125M-200G score isn't reproducable HOT 2
- Whole stack didn't work with python 3.7 but does with python 3.8
- In order to get evaluation to work i had to change config.json
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 mengzi-retrieval-lm.