Workbench
Collection
Untested and unfinished models. Works in progress.
•
8 items
•
Updated
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 |
- Downloads last month
- 2,702
Dataset used to train TeeZee/NEBULA-XB-v1.0_SFT_2_epoch
Collection including TeeZee/NEBULA-XB-v1.0_SFT_2_epoch
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard63.050
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard85.070
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard65.410
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard52.060
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard82.240
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard0.300