RyanYr
/

grpo-respL-dapo-r1-qwen2.5math-1.5B-base-mbs64-n4_actor

Model card Files Files and versions Community

grpo-respL-dapo-r1-qwen2.5math-1.5B-base-mbs64-n4_actor / data.pt

Commit History

Save model at global step 120

5fe77d3
verified

RyanYr commited on May 13

Save model at global step 80

3f050d5
verified

RyanYr commited on May 13

Save model at global step 40

7b54f77
verified

RyanYr commited on May 13