Comments (11)
That's surprising given that it works for the other examples. It's very hard to help without being able to reproduce.
- Does it always error out on the same examples? if so can you send some to me?
- can you try
export OPENAI_MAX_CONCURRENCY=1
and see if the error persits - can you paste the error/warnings you get during the annotation?
Thanks!
from alpaca_eval.
Thank you for your reply! I will try again and give more information latter.
from alpaca_eval.
I have some questions about the dropping of samples during the evaluation of Alpaca eval. Is it normal to have some dropped samples, or is the normal condition that all 805 samples are correct?
from alpaca_eval.
Usually we don't drop anything, but it may happen that GPT4 API fails and then you drop 2-3 examples, which we don't care much about. But you are dropping 500 examples here, which is definitely not expected and I wouldn't trust the win-rates you are currently getting.
from alpaca_eval.
I think it could be an issue with my API or occurring during the request process. Now I have a unified platform for requesting GPT-4. The process involves uploading a text file with prompts and inputs, and the platform will return the generated results from GPT-4. Then, I utilize the results from GPT-4 to parse and calculate the win rate. Do you have any suggestions on how I should unpack and execute the process you've encapsulated?
from alpaca_eval.
This is part of the process of requesting GPT-4, and no other errors have occurred. However, the following error subsequently appeared.
from alpaca_eval.
Do you have the error if you use the base OpenaAI api? Please try without using lonlie.plus7
, I can't help for other APIs
from alpaca_eval.
This is likely your server error not an AlpacaEval error. If you can reproduce the error with the openai base then feel free to reopen.
from alpaca_eval.
Thank you for all your patient responses. I'm currently trying out the openai base API to test the results.
from alpaca_eval.
Have you found a solution?
from alpaca_eval.
Have you found a solution?
I used to use an API provided by my lab, which required setting up an openai_api_base. This was a URL that may not have been the official API. When I switched to the official OPENAI GPT-4 API, the problem was resolved.
from alpaca_eval.
Related Issues (20)
- With unstable GPT-4 API, I encounterd a tricky problem HOT 1
- With unstable GPT-4 API, I encounterd a tricky problem HOT 2
- openai_configs.yaml when using Azure only HOT 7
- Confusion in Model Evaluation Results Due to GPT Updates HOT 2
- How instruction_difficulty feature is obtained HOT 1
- Llama-3-Instruct not using official prompt template? HOT 1
- Unable to reproduce results HOT 1
- Missing item in results/llama-2-70b-chat-hf HOT 1
- Missing result file in notebook HOT 1
- How to solve the problem of null appearing in the evaluation results HOT 3
- What to do if the log prob is not returned? HOT 7
- How to get the LC Win Rate in AlpacaEval 1.0 version? HOT 4
- How to change cache path when evaluating multi-models HOT 1
- The n_total of n_total result is not 805 HOT 6
- Overly High Win Rate for Alpaca v2 on mistral 7b orpo HOT 12
- How to use AE1 to evaluate model HOT 2
- possibility of adding llama3-70b as the evaluator? HOT 3
- Alpaca Evaluation Instruction Difficulty used also for Custom Evaluation Dataset HOT 3
- Add Phi 3 models HOT 3
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 alpaca_eval.