TeeZee/NEBULA-XB-v1.0_SFT_2_epoch
Experiment, can DUS be taken one or more steps further?
Technical notes:
- pretrained model NEBULA-XB-v1.0 finetuned on 30k entries from Merge_Glue dataset
- 18 layers removed from both models of finetuned GALAXY-XB-v03
- model has 108 layers (((48-12)*2)-18)*2 = 108
- second step in scaling DUS procedure
To evaluate
- model performance after merge, should be a little lover that GALAXY finetuned on 50k of slimorca
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 58.02 |
| AI2 Reasoning Challenge (25-Shot) | 63.05 |
| HellaSwag (10-Shot) | 85.07 |
| MMLU (5-Shot) | 65.41 |
| TruthfulQA (0-shot) | 52.06 |
| Winogrande (5-shot) | 82.24 |
| GSM8k (5-shot) | 0.30 |