Reasoning on Mathematical Reasoning (train)
1,177.8MTL (Loss)SFT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| SFTTraining Time=9m 36s2025.09 | 1,177.8 | 75.8 | |
| R1-Qwen-7B (Base)Training Time=/2025.09 | 1,244 | 76.9 | |
| RL (GRPO)Training Time=4h 09m 35s2025.09 | 1,481.9 | 93.2 | |
| FARLTraining Time=4h 22m 53s2025.09 | 1,660.8 | 92.4 |