Comments (9)
Hi, are you using the latest code?
from openfedllm.
I think that this might has been addressed by 4e9a949. Please check the modification in show_results_mt.py.
from openfedllm.
Hi, are you using the latest code?
Yes, the above results are from running the latest code, where line 32 of show_results_mt.py is "mtbench".
from openfedllm.
emmm. We did not come across such error before. Could you please provide your screen shot during running gen_judge_mtbench.py?
from openfedllm.
Hello, would you please provide the error message when running "python gen_judge_mtbench.py --judge_model gpt-4-1106-preview --model_list alpaca-gpt4_20000_fedavg_c20s2_i10_b16a1_l512_r32a64_20240313104822_200"?
Please make sure that you have a good internet connection and are using the correct OPENAI_API_KEY.
from openfedllm.
from openfedllm.
oh, this is related to the issue of network connection between your working device and OpenAI, but not related to the code.
from openfedllm.
This error indicates that your device fails to connect gpt-4 api, therefore, no judgement is received. Please make sure your network connection is well and you will see the judgment of gpt-4 printed on the screen.
The following is an example:
The AI assistant's response is a well-structured and engaging travel blog post about a trip to Hawaii. It effectively highlights cultural experiences, such as participating in a hula lesson and trying traditional Hawaiian food, and must-see attractions like Haleakala National Park and Hanauma Bay. The post is informative, providing insights into Hawaiian heritage and the unique biodiversity of the islands. The language used is descriptive and evocative, painting a vivid picture of the experiences and scenery.\n\nThe response is relevant to the user's request, focusing on cultural aspects and notable attractions. It is accurate in its descriptions of Hawaiian culture and the natural beauty of the islands. The depth of the post is appropriate for a blog entry, offering personal insights and recommendations without overwhelming the reader with excessive detail. Creativity is shown in the way the assistant weaves together personal experiences with factual information to create a narrative that is both informative and personal. The level of detail is sufficient to engage the reader and provide a sense of what a trip to Hawaii might entail.\n\nOverall, the response is a strong example of a travel blog post that would likely be helpful and enjoyable for someone interested in visiting Hawaii. It meets the criteria of helpfulness, relevance, accuracy, depth, creativity, and level of detail.\n\nRating: [[8]]
from openfedllm.
Ok, I see. Thank you very much for your patient reply.
from openfedllm.
Related Issues (10)
- train_loss HOT 6
- Evaluation on other datasets? HOT 2
- Continue training according to checkpoint HOT 1
- How can i perform local training using the OpenFedLLM? HOT 3
- Does the framework support multi-gpu training? HOT 3
- Request for Close-ended evaluation scripts HOT 1
- Need help with evaluation HOT 2
- Error in FedProx loss computation
- Run myself Data 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 openfedllm.