Open Issues Need Help
View All on GitHub AI/ML • Advanced Reasoning Models
Query about the learning rate about 1 year ago
AI Summary: The task is to find and report the learning rate used to train the Qwen3-4B models in the POLARIS project, based on the provided project README and issue description. The response should be concise and address the user's question about the difficulty of improving post-trained models using GRPO.
Complexity:
2/5
good first issue
ChenxinAn-fdu/POLARIS ChenxinAn-fdu/POLARIS Scaling RL on advanced reasoning models
Open project →
300
Scaling RL on advanced reasoning models
Python