[Submission] Assignment 2 GRPO Training for the Countdown Task - Giang Nguyen

[giangntt]

Student Name

Giang Nguyen

Model Length

256

Accuracy

55.76%

Improvement Description

Multi-round training, with checkpoint selection and optimizer reset; warm-up with Dr.GRPO.

Detailed Write-up

No response

GPU Hours

No response

Submission Agreement

• I confirm that these results are from my own work

[github-actions]

✅ Your submission has been processed and added to the leaderboard! View it at: https://newturing.github.io/leaderboard/