Medical Reasoning on Medical Reasoning
59.7pass@1FedAvg-GRPO
Evaluation Results
| Method | Links | |
|---|---|---|
| FedAvg-GRPOLocal steps (τ)=10, Model=Llama3.2-3B-Instruct, Aggregation method=Balanced method, Swap period=22026.04 | 59.7 | |
| FedAvg-PubSwapLocal steps (τ)=40, Model=Llama3.2-3B-Instruct, Aggregation method=Balanced method, Swap period=22026.04 | 59.5 | |
| FedAvg-GRPOLocal steps (τ)=40, Model=Llama3.2-3B-Instruct, Aggregation method=Balanced method, Swap period=22026.04 | 58.9 | |
| FedAvg-PubSwapLocal steps (τ)=90, Model=Llama3.2-3B-Instruct, Aggregation method=Balanced method, Swap period=22026.04 | 58.5 | |
| FedAvg-PubSwapLocal steps (τ)=10, Model=Llama3.2-3B-Instruct, Aggregation method=Balanced method, Swap period=22026.04 | 58.3 | |
| FedAvg-PubSwapLocal steps (τ)=120, Model=Llama3.2-3B-Instruct, Aggregation method=Balanced method, Swap period=22026.04 | 58.1 | |
| FedAvg-GRPOLocal steps (τ)=90, Model=Llama3.2-3B-Instruct, Aggregation method=Balanced method, Swap period=22026.04 | 57.9 | |
| FedAvg-GRPOLocal steps (τ)=120, Model=Llama3.2-3B-Instruct, Aggregation method=Balanced method, Swap period=22026.04 | 57.7 | |
| Base modelLocal steps (τ)=10, Model=Llama3.2-3B-Instruct, Aggregation method=Balanced method, Swap period=22026.04 | 49.2 | |
| Base modelLocal steps (τ)=40, Model=Llama3.2-3B-Instruct, Aggregation method=Balanced method, Swap period=22026.04 | 49.2 | |
| Base modelLocal steps (τ)=90, Model=Llama3.2-3B-Instruct, Aggregation method=Balanced method, Swap period=22026.04 | 49.2 | |
| Base modelLocal steps (τ)=120, Model=Llama3.2-3B-Instruct, Aggregation method=Balanced method, Swap period=22026.04 | 49.2 |