-
Notifications
You must be signed in to change notification settings - Fork 9
Open
Labels
bugSomething isn't workingSomething isn't working
Description
Description of the bug
There is not grpo_output_file argument in process_annotation_direct_attribution.py, rather than sft_output_file. How to get grpo_output_file? Is the same?
cd ../data_process python process_annotation_direct_attribution.py \ --data_dir ../data \ --input_file sotopia_pi_bc_episodes_annotated.jsonl \ --reward_output_file sotopia_pi_bc_episodes_reward.json \ --grpo_output_file sotopia_pi_bc_episodes_grpo.json
Steps To Reproduce
cd ../data_process
python process_annotation_direct_attribution.py
--data_dir ../data
--input_file sotopia_pi_bc_episodes_annotated.jsonl
--reward_output_file sotopia_pi_bc_episodes_reward.json
--grpo_output_file sotopia_pi_bc_episodes_grpo.json
Additional Information
No response
Metadata
Metadata
Assignees
Labels
bugSomething isn't workingSomething isn't working