Modelpublic

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

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face

0likes18downloads

Model Card

qwen3-8b-biology-rlsd-ema005

Fine-tuned from Qwen/Qwen3-8B with RLSD (EMA 0.05) 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
64.25%	100	64.25%	100

[image]

step	mean@16
10	32.00%
20	35.62%
30	47.12%
40	52.25%
50	55.62%
60	55.75%
70	59.88%
80	61.38%
90	55.50%
100	64.25%

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

W&B run: run-20260630_224949-g2gxclf3

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