Preference Alignment on WebGPT (test)
61.24AccuracyFedPDPO
Evaluation results
| Method | Links | |
|---|---|---|
| FedPDPOBackbone=TinyLlama-1.1B, Federated Strategy=FedPDPO, Optimization Algorithm=DPO, Number of Clients=32026.03 | 61.24 | |
| FedPer(+DPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedPer, Optimization Algorithm=DPO, Number of Clients=32026.03 | 56.43 | |
| FedRep(+DPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedRep, Optimization Algorithm=DPO, Number of Clients=32026.03 | 55.81 | |
| Per-FedAvg(+DPO)Backbone=TinyLlama-1.1B, Federated Strategy=Per-FedAvg, Optimization Algorithm=DPO, Number of Clients=32026.03 | 55.67 | |
| FedAMP(+DPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedAMP, Optimization Algorithm=DPO, Number of Clients=32026.03 | 54.92 | |
| FedAvg(+DPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedAvg, Optimization Algorithm=DPO, Number of Clients=32026.03 | 54.12 | |
| FedPer(+PPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedPer, Optimization Algorithm=PPO, Number of Clients=32026.03 | 53.18 | |
| FedRep(+PPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedRep, Optimization Algorithm=PPO, Number of Clients=32026.03 | 52.47 | |
| Per-FedAvg(+PPO)Backbone=TinyLlama-1.1B, Federated Strategy=Per-FedAvg, Optimization Algorithm=PPO, Number of Clients=32026.03 | 52.34 | |
| FedAMP(+PPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedAMP, Optimization Algorithm=PPO, Number of Clients=32026.03 | 51.58 | |
| FedAvg(+PPO)Backbone=TinyLlama-1.1B, Federated Strategy=FedAvg, Optimization Algorithm=PPO, Number of Clients=32026.03 | 50.85 |