You can deploy this model and start earning money today!

WooYoungSeok/
rm-deepseek-r1-qwen3-8b-0622

Name: rm-deepseek-r1-qwen3-8b-0622
Availability: InStock

safetensors

qwen3

text-classification

deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

finetune

apache-2.0

Views

No views yet

rm-deepseek-r1-qwen3-8b-0622

Role: RM Base model: deepseek-ai/DeepSeek-R1-0528-Qwen3-8B

Training data (0622 4-way split, no leakage)

Split	Rows	Used as
train_rm1	806	RM train (1/2)
train_rm2	805	RM train (1/2) / Verifier test
train_verifier1	805	Verifier train (1/2) / RM val
train_verifier2	805	Verifier train (1/2) / RM test

This checkpoint was trained on train_rm1+train_rm2 with train_verifier2 as the held-out test set (and the counterpart split used as validation for best-checkpoint selection).

Train objective: SFT to emit aligned / not_aligned after the standard "You are a math solution evaluator..." system prompt.

Test-set performance (train_verifier2.json, N=1610, balanced)

Metric	Value
Accuracy	0.8497
Macro F1	0.8496
Parse failures	0 / 1610

License

Apache-2.0. Bundled training data licenses follow each source dataset (MathEDU, Stepwise Verification, MathClean, EIC).

WooYoungSeok/rm-deepseek-r1-qwen3-8b-0622

rm-deepseek-r1-qwen3-8b-0622

Training data (0622 4-way split, no leakage)

Test-set performance (train_verifier2.json, N=1610, balanced)

License

WooYoungSeok/
rm-deepseek-r1-qwen3-8b-0622