XINLI1997 commited on
Commit
8b292b7
·
verified ·
1 Parent(s): 900799a

Model card: training hardware is 4x RTX 4090 D

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -24,7 +24,7 @@ GRPO-trained reference checkpoint from **WirelessMathBench-XL: An Auditable Benc
24
  ## Model
25
 
26
  - **Base:** [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B). Initialised from the **Qwen2.5-7B** base checkpoint (no SFT warm-start).
27
- - **Training:** GRPO with [EasyR1](https://github.com/hiyouga/EasyR1) on the WirelessMathBench-XL train split (3,227 problems), 40 epochs / 240 steps, composite reward 0.1 × format + 0.9 × verifier accuracy, AdamW (lr 1e-6, cosine), KL coefficient 0.01, 4 × NVIDIA A6000. See Appendix B of the paper.
28
  - **Precision:** bfloat16.
29
 
30
  ## Results
 
24
  ## Model
25
 
26
  - **Base:** [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B). Initialised from the **Qwen2.5-7B** base checkpoint (no SFT warm-start).
27
+ - **Training:** GRPO with [EasyR1](https://github.com/hiyouga/EasyR1) on the WirelessMathBench-XL train split (3,227 problems), 40 epochs / 240 steps, composite reward 0.1 × format + 0.9 × verifier accuracy, AdamW (lr 1e-6, cosine), KL coefficient 0.01, 4 × NVIDIA RTX 4090 D. See Appendix B of the paper.
28
  - **Precision:** bfloat16.
29
 
30
  ## Results