Instruction-tuning on Alpaca-style instruction-tuning 5K samples (held-out)
1.342Cross-Entropy Loss (Std)Sophia
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| SophiaStandard Setting=b512, lr 2e−5, Corrected Setting=b512, lr 2e−52026.05 | 1.342 | 1.342 | 0 |
| Method | Links | |||
|---|---|---|---|---|
| SophiaStandard Setting=b512, lr 2e−5, Corrected Setting=b512, lr 2e−52026.05 | 1.342 | 1.342 | 0 |