-
-
Notifications
You must be signed in to change notification settings - Fork 108
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat: Enabling automation of experiments running v2.0 #469
base: main
Are you sure you want to change the base?
Conversation
b44bef5
to
21a99d2
Compare
scripts/exp/ablation/env/basic.env
Outdated
@@ -0,0 +1,5 @@ | |||
if_using_vector_rag=False |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
the environment should capitalized.
@@ -0,0 +1,8 @@ | |||
{ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why do you submit this file?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I thought since this was not to be merged I could show how the json is organised for now.
I will hide it in the next commit.
@@ -0,0 +1,136 @@ | |||
#!/bin/bash | |||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
What is this file for?
.gitignore
Outdated
@@ -117,6 +117,7 @@ venv/ | |||
ENV/ | |||
env.bak/ | |||
venv.bak/ | |||
.huaxia_env |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
what is this for? is it necessary?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for the feedback! Was about to hide this.
…D-Agent into automated-evaluation
@xisen-w please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.
Contributor License AgreementContribution License AgreementThis Contribution License Agreement (“Agreement”) is agreed to by the party signing below (“You”),
|
scripts/exp/ablation/README.md
Outdated
@@ -0,0 +1,9 @@ | |||
# Introduction | |||
|
|||
| name | .env | desc | |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this file is not complete
scripts/exp/tools/README.md
Outdated
1. Ensure the scripts have execution permissions: | ||
|
||
``` | ||
chmod +x scripts/exp/tools/run_envs.sh |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
You can commit the file permission to github directly instead of writting them in README.md
scripts/exp/tools/README.md
Outdated
1. Ensure the scripts are executable: | ||
|
||
``` | ||
chmod +x scripts/exp/tools/run_envs.sh |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
same as above
scripts/exp/tools/README.md
Outdated
### Notes | ||
* Scale parallel processes as needed using the -j parameter. | ||
* Avoid errors by ensuring .env files are correctly formatted. | ||
* Modify test_system.sh to meet your project's specific needs. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
When should we modifiy the script?
@@ -0,0 +1,83 @@ | |||
import os |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Will the env name (e.g. basic, max, pro) displayed in the collected results?
scripts/exp/tools/test_system.sh
Outdated
mkdir -p "$TEST_DIR/logs" | ||
|
||
# Define paths | ||
ENV_DIR="/home/v-xisenwang/RD-Agent/scripts/exp/ablation/env" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think it would be better to use config for the path instead of hard-coded
scripts/exp/tools/README.md
Outdated
|
||
``` | ||
python collect.py --log_path logs --output_name summary.json | ||
``` |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think it would be better to give an example of the collected results.
scripts/exp/ablation/env/pro.env
Outdated
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Here, it also needs to add the path to the knowledge base.
scripts/exp/ablation/env/max.env
Outdated
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Here, it needs to add the path to the knowledge base.
scripts/exp/ablation/env/max.env
Outdated
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
KG_IF_USING_VECTOR_RAG
here should be set to false
.
Description
This PR provides the automation of experimentation and result collection.
Motivation and Context
This change is required to streamline the process of running experiments, reducing manual setup and potential errors. It solves the problem of inconsistent experiment configurations and enhances the automation capabilities of the system.
How Has This Been Tested?
run_envs.sh
andtest_system.sh
script runs without errors and correctly sets up the environment for experiments.Screenshots of Test Results (if appropriate):
Types of changes
📚 Documentation preview 📚: https://RDAgent--469.org.readthedocs.build/en/469/