Preference Alignment on PyDPO (test)
94.32AccuracyFedPDPO
Evaluation Results
| Method | Links | |
|---|---|---|
| FedPDPOBackbone=TinyLlama-1.1B, Federated Strategy=FedPDPO, Optimization Algorithm=DPO, Number of Clients=32026.03 | 94.32 | |
| FedPer(+DPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedPer, Optimization Algorithm=DPO, Number of Clients=32026.03 | 93.05 | |
| FedRep(+DPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedRep, Optimization Algorithm=DPO, Number of Clients=32026.03 | 92.54 | |
| Per-FedAvg(+DPO)Backbone=TinyLlama-1.1B, Federated Strategy=Per-FedAvg, Optimization Algorithm=DPO, Number of Clients=32026.03 | 92.38 | |
| FedAvg(+DPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedAvg, Optimization Algorithm=DPO, Number of Clients=32026.03 | 91.8 | |
| FedAMP(+DPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedAMP, Optimization Algorithm=DPO, Number of Clients=32026.03 | 91.23 | |
| FedPer(+PPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedPer, Optimization Algorithm=PPO, Number of Clients=32026.03 | 90.54 | |
| Per-FedAvg(+PPO)Backbone=TinyLlama-1.1B, Federated Strategy=Per-FedAvg, Optimization Algorithm=PPO, Number of Clients=32026.03 | 89.86 | |
| FedRep(+PPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedRep, Optimization Algorithm=PPO, Number of Clients=32026.03 | 89.71 | |
| FedAvg(+PPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedAvg, Optimization Algorithm=PPO, Number of Clients=32026.03 | 89.12 | |
| FedAMP(+PPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedAMP, Optimization Algorithm=PPO, Number of Clients=32026.03 | 88.45 |