Instruction Following on IFEVAL (SSR, HSR)
75.7SSRPT-GRPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PT-GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.06 | 75.7 | 65.8 | |
| MDP-GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.06 | 75.3 | 64.1 | |
| DA-GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.06 | 75.2 | 64.7 | |
| DA-PT-GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.06 | 74.8 | 64.3 | |
| MT-GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.06 | 73.9 | 63.7 | |
| GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.06 | 73.7 | 62.4 | |
| DA-PT-GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.06 | 71.5 | 60.4 | |
| MDP-GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.06 | 71.3 | 59.8 | |
| DA-GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.06 | 71.2 | 62.5 | |
| PT-GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.06 | 70.1 | 61.3 | |
| MT-GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.06 | 68.1 | 59.1 | |
| GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.06 | 66.1 | 58.5 | |
| BaselineModel=Gemma-2-2B-Instruct, Group Size (G)=82026.06 | 56.7 | 45.1 | |
| BaselineModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.06 | 54.2 | 46.8 |