Skip to main content

Qwen2.5-3b-it-search-r1-reproduce

Created on June 3|Last edited on June 3

Evaluation


100200300400500Step0.10.150.20.25
100200300400500Step0.240.260.280.30.32
100200300400500Step0.060.070.080.090.10.11
100200300400500Step0.360.380.4
100200300400500Step0.50.520.540.560.58
100200300400500Step0.340.350.360.370.380.390.4
Run: qwen2.5-3b-it_rm-searchR1-like-sgl-multiturn-2025-06-01-12-46
1


Response Length


Run: qwen2.5-3b-it_rm-searchR1-like-sgl-multiturn-2025-06-01-12-46
1



Training Reward


Run: qwen2.5-3b-it_rm-searchR1-like-sgl-multiturn-2025-06-01-12-46
1


Run: qwen2.5-3b-it_rm-searchR1-like-sgl-multiturn-2025-06-01-12-46
1