Modelpublic

SeongryongJung/qwen3-4b-biology-grpo

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face

0likes13downloads

Model Card

qwen3-4b-biology-grpo

Fine-tuned from Qwen/Qwen3-4B with GRPO on the biology split.

Validation Performance

Metric: val-aux/sciknoweval/reward/mean@16 from 10-step validation logs.

best mean@16	best step	final mean@16	final step
54.62%	70	50.12%	100

[image]

step	mean@16
10	35.62%
20	37.75%
30	39.38%
40	49.38%
50	53.12%
60	54.37%
70	54.62%
80	49.88%
90	49.25%
100	50.12%

Files included with this repo:

—metrics.json: parsed validation summary
—eval_mean16.csv: step-level validation curve data
—eval_mean16.png: validation curve plot

Important: the uploaded weights are the final global_step_100/actor checkpoint. If best step is earlier than 100, the best validation point is reported for tracking, but the corresponding actor weights may not be retained locally.

Checkpoint source: /mnt/mole/SDPO/L2T/checkpoints/datasets/sciknoweval/biology/qwen3gen-biology-GRPO-Qwen-Qwen3-4B-mbs8-train64-rollout8-lr1e-6-vllm0.8

W&B run: run-20260629_210338-dnw0fpte

This upload uses global_step_100/actor converted from VERL FSDP shards to Hugging Face format.