Can you provide a search_r1 example for agent-linghting v2?

[hzy312]

I can see the example of search_r1 is for v1 api, such as n_workers (n_runners in v2) and url training dataset?
Can you explain the new features?
Can you provide a search_r1 example for agl v2?
Thanks.

[ultmaster]

@SiyunZhao do you have time for the migration?

[hzy312]

FYI:
I run python search_r1_agent.py, then bash train.sh.
It hang like this:

[SiyunZhao]

@SiyunZhao do you have time for the migration?

Yes, I’m available to do the migration.

[SiyunZhao]

FYI: I run python search_r1_agent.py, then bash train.sh. It hang like this:

Seems like it’s hanging during validation.
Do you have any logs printed from search_r1_agent.py showing the dialogue?

[hzy312]

It is just like this, no dialogue.
I have not read the code, so i do not know what happended😂

[hzy312]

@SiyunZhao Hi, I use agl v.0.1.2 to reproduce the search_r1.
I use the env set in scripts/setup_stable_gpu.sh.
But it kept throw errors like:

Do you have any ideas on this pydantic error for numpy.ndarray?