Modelpublic

SeongryongJung/qwen3-8b-chemistry-rlsd-ema005

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face

0likes11downloads

Model Card

qwen3-8b-chemistry-rlsd-ema005

Fine-tuned from Qwen/Qwen3-8B with RLSD (EMA 0.05) on the chemistry 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
74.38%	100	74.38%	100

[image]

step	mean@16
10	45.95%
20	60.57%
30	67.65%
40	68.75%
50	70.18%
60	72.32%
70	71.61%
80	72.20%
90	73.18%
100	74.38%

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/chemistry/qwen3gen-chemistry-RLSD-Qwen-Qwen3-8B-mbs8-decay0-ema0.05-train64-rollout8-lr1e-6-vllm0.8

W&B run: run-20260630_122838-yvmohps3

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