Comments (2)
Great questions!
-
Concerning the rate limit, there are 3 ways to avoid/mitigate it.
- Decreasing number of processes: by default we use 4 concurrent processes for querying GPT4. This will hit the rate limit faster. If that's an issue you can change it in the evaluators configs. e.g. add
num_procs: 2
in the completion kwargs - Increasing sleep time: we are already adding a 2 seconds sleep time here. If this is not sufficient for you, you can change it in the evaluators configs. e.g. add
sleep_time: 10
in the completion kwargs - Using multiple API keys: in case you have multiple API keys you can set them separated by commas
OPENAI_API_KEYS=key1,key2
and we will switch between them when you get rate limited.
- Decreasing number of processes: by default we use 4 concurrent processes for querying GPT4. This will hit the rate limit faster. If that's an issue you can change it in the evaluators configs. e.g. add
-
When you hit a rate limit we will simply retry (as seen in the warning) so that's not the issue. If there are missing evaluation results it typically means that the annotations could not be parsed. we also raise a warning for that so you see the reason in your terminal!
Feel free to reopen if you have further questions
from alpaca_eval.
For future reference, here's the way to deal with multiple keys now: https://github.com/tatsu-lab/alpaca_eval/tree/main/client_configs
one can also use Azure
from alpaca_eval.
Related Issues (20)
- The code for computing instruction difficulty HOT 1
- confused about openai API HOT 1
- Preference doesn't match log_probs in `annotations.json` HOT 1
- Why is max_num_seqs allowed here? HOT 1
- tensor_parallel_size can not work HOT 1
- How to solve the problem of null appearing in the evaluation results? Thank you very much HOT 3
- ERROR:root:Error while parsing completion: HOT 1
- Evaluating a self hosted LLM through an API. HOT 1
- Details on Training GLM for Length-Controlled Winrate HOT 3
- cannot reindex HOT 3
- Discrepancy between alpaca leaderboard and Chatbot arena ELO HOT 1
- ValueError: Trailing data HOT 1
- AssertionError
- Encountering Error about cannot reindex on an axis with duplicate labels HOT 2
- Negative Correlation while using `alpaca_eval analyze_evaluators` HOT 1
- Too difficult to use! It's much worse than MT bench! HOT 2
- Argument `do_sample` is removed from `vllm_local_completions` HOT 1
- assert output_path is not None and name in leaderboard
- Why do we set do_sample to true during evaluation? HOT 1
- Extra '\n' in the prompt of Llama-3-Instruct-8B-SimPO 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 alpaca_eval.