Topic Classification on TREC
95.6AccuracyFZOO
Evaluation results
| Method | Links | |
|---|---|---|
| FZOOBackbone=RoBERTa-large (350M), k-shot setting=512, Optimization Protocol=Zeroth-Order, Training Steps=20k, Batch Size=16, Precision=FP162026.06 | 95.6 | |
| GRZOBackbone=RoBERTa-large (350M), k-shot setting=512, Optimization Protocol=Zeroth-Order, Training Steps=20k, Batch Size=16, Precision=FP162026.06 | 94.7 | |
| MeZOBackbone=RoBERTa-large (350M), k-shot setting=512, Optimization Protocol=Zeroth-Order, Training Steps=20k, Batch Size=16, Precision=FP162026.06 | 94.3 | |
| LP(FO)Backbone=RoBERTa-large (350M), k-shot setting=512, Optimization Protocol=Linear Probing (First-Order), Training Steps=20k, Batch Size=16, Precision=FP162026.06 | 89.4 | |
| FT(FO)Backbone=RoBERTa-large (350M), k-shot setting=512, Optimization Protocol=Fine-Tuning (First-Order), Training Steps=20k, Batch Size=16, Precision=FP162026.06 | 85 | |
| Zero-shotBackbone=RoBERTa-large (350M), k-shot setting=5122026.06 | 32 |