What has been done to verify that this works as intended?
enhance the prompts to strickly follow the filename output format;
add the filename as candidate lists if the output is a single string.
Why is this the best possible solution? Were any other approaches considered?
We should let the agent to generate the filename candidates in the correct format.
How does this change affect users? Describe intentional changes to behavior and behavior that could have accidentally been affected by code changes. In other words, what are the regression risks?
Do we need any specific form for testing your changes? If so, please attach one.
[? What is the description of this project? (Optional)] train vit using mnist
[? Hi, what are your requirements?] train vit using mnist datasets
Does this change require updates to documentation? If so, please file an issue here and include the link below.
No
Before submitting this PR, please make sure you have:
[x] confirmed all checks still pass OR confirm CI build passes.
[x] verified that any code or assets from external sources are properly credited in comments and/or in
the credit file.
Closes https://github.com/MLSysOps/MLE-agent/issues/71
What has been done to verify that this works as intended?
Why is this the best possible solution? Were any other approaches considered?
We should let the agent to generate the filename candidates in the correct format.
How does this change affect users? Describe intentional changes to behavior and behavior that could have accidentally been affected by code changes. In other words, what are the regression risks?
Do we need any specific form for testing your changes? If so, please attach one.
[? What is the description of this project? (Optional)] train vit using mnist [? Hi, what are your requirements?] train vit using mnist datasets
Does this change require updates to documentation? If so, please file an issue here and include the link below.
No
Before submitting this PR, please make sure you have: