This is openchat/openchat-3.5-0106, tuned with DPO on a tiny subset Nectar. Only 200 steps, so nowhere close to a full epoch.
Careful attention was paid to make sure the chat template was followed properly.
Summary of versions:
- 200 steps, no filtering on Nectar dataset, 5e-5 learning rate
- empty repo, failed training. ignore it
- 500 steps, no filtering on Nectar dataset, 5e-5 learning rate (same as 1 but with more steps)
- 500 steps, filtered dataset to only include multi-chat-turn examples, used 4th ranking response as the "rejected" instead of 3rd, filtered out "good_natured=False", 5e-5 learning rate
- 5000 steps (over a full epoch), filtered dataset to only include multi-chat-turn examples, used 4th ranking response as the "rejected" instead of 3rd, filtered out "good_natured=False", 5e-6 learning rate. Same as 0.4 but with 10x the steps, and 1/10th the learning rate
- 500 steps, filtered dataset to only include multi-chat-turn examples, used 4th ranking response as the "rejected" instead of 3rd, filtered out "good_natured=False", 5e-5 learning rate. Same as 0.5 but with 1/10th the steps, and 10x the learning rate
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 69.94 |
AI2 Reasoning Challenge (25-Shot) | 66.21 |
HellaSwag (10-Shot) | 82.99 |
MMLU (5-Shot) | 65.17 |
TruthfulQA (0-shot) | 54.22 |
Winogrande (5-shot) | 81.37 |
GSM8k (5-shot) | 69.67 |
- Downloads last month
- 31
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for andysalerno/openchat-nectar-0.1
Dataset used to train andysalerno/openchat-nectar-0.1
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard66.210
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard82.990
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard65.170
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard54.220
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard81.370
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard69.670