Skip to content

[Submission] Assignment 2 GRPO Training for the Countdown Task - Giang Nguyen #7

@giangntt

Description

@giangntt

Student Name

Giang Nguyen

Model Length

512

Accuracy

64.84%

Improvement Description

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

Detailed Write-up

Assignment-2-Report-Giang-Nguyen.pdf

GPU Hours

1 hour Ada 6000

Submission Agreement

  • I confirm that these results are from my own work

Metadata

Metadata

Assignees

No one assigned

    Labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions