Static-R0 Matched GRPO on RaR-Medicine — step 12
This is the policy after 12 global optimizer updates of the matched static-rubric GRPO run (planned total: 48). It is intentionally separate from the OnlineRubrics/dynamic-rubric checkpoints.
Experiment identity
- Method:
static_r0_matched - Reward source:
rar_static_r0_only - Domain: Medicine
- Training data: RaR-Medicine, 1,500 prompts
- Seed: 11
- Policy:
Qwen/Qwen3-4B-Instruct-2507 - Base revision:
cdbee75f17c01a7cc42f958dc650907174af0554 - Thinking: disabled
- GRPO global prompt batch: 96
- Rollouts per prompt: 16
- Learning rate: 5e-06
The root files are a BF16 Transformers export for inference. The
original_checkpoint/ directory contains the exact original veRL/FSDP policy
parameter checkpoint and its tokenizer/configuration files. Optimizer,
trainer, and data-loader state are intentionally not published; the complete
resume checkpoint remains on Daisy.
from transformers import AutoModelForCausalLM, AutoTokenizer
repo_id = "HYU-NLP-EVAL/qwen3-4b-rar-medicine-static-r0-matched-seed11-step-012"
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(
repo_id, torch_dtype="bfloat16", device_map="auto"
)
This is an intermediate research checkpoint, not a clinical model. No medical capability or safety claim is made.
Original actor parameter SHA256: 0f1cacfffb02429db7c7f2802d2ceeda9513b355e6b51aaaa8db83c6d788478f