od2961/qwen2.5-Math-1.5b-drgrpo-readmeflash-a6000-5epoch-seed43
This repo stores organized DR.GRPO checkpoints for seed 43 from our
Qwen2.5-Math-1.5B readme-flash math-reasoning training run.
Layout
checkpoints/step_XXXXX/: exported model checkpoints ready for inferenceeval_results/: per-benchmark JSON outputs saved at eval boundariesmetadata/checkpoints_index.json: machine-readable checkpoint manifestmetadata/run_manifest.json: local run provenance
Source Run Root
- Local save root:
/n/fs/similarity/maxent-grpo/var/data/oat_zero_exact_1p5b_20260412_160206_seed43 - Objective:
dr.grpo
Available Checkpoints
| Step | Size (GiB) | Eval files |
|---|---|---|
step_00000 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00016 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00032 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00048 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00064 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00080 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00096 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00112 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00128 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00144 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00160 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00176 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00192 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00208 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00224 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00240 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00256 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00272 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00288 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00304 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00320 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00336 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00352 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00368 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00384 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00400 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00416 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00432 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00448 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00464 |
2.89 |
aime, amc, math, minerva, olympiad_bench |
step_00466 |
2.89 |
aime, amc, math, minerva, olympiad_bench |