Instruction Following on Custom (test)
71.4SSRPT-GRPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PT-GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.06 | 71.4 | 30.6 | |
| DA-PT-GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.06 | 70.8 | 33.4 | |
| DA-GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.06 | 70.7 | 32.6 | |
| MDP-GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.06 | 70.3 | 32.8 | |
| MT-GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.06 | 68.6 | 29.6 | |
| GRPOModel=Gemma-2-2B-Instruct, Group Size (G)=82026.06 | 68.4 | 29 | |
| DA-PT-GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.06 | 66.3 | 25.4 | |
| DA-GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.06 | 66.1 | 24.9 | |
| MDP-GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.06 | 65.8 | 25.2 | |
| MT-GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.06 | 65.4 | 24.6 | |
| GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.06 | 65.1 | 24.8 | |
| PT-GRPOModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.06 | 64.7 | 23.6 | |
| BaselineModel=Llama-3.2-3B-Instruct, Group Size (G)=82026.06 | 60.3 | 20.8 | |
| BaselineModel=Gemma-2-2B-Instruct, Group Size (G)=82026.06 | 54.8 | 18.8 |