|
--- |
|
license: apache-2.0 |
|
base_model: openchat/openchat-3.5-0106 |
|
datasets: |
|
- berkeley-nest/Nectar |
|
--- |
|
This is openchat/openchat-3.5-0106, tuned with DPO on a subset Nectar. This time with 5000 steps, a full epoch. |
|
|
|
Careful attention was paid to make sure the chat template was followed properly. |
|
|
|
Data selection and filtering: |
|
- filtered dataset to only include examples with multiple turns, to preserve strength in multi-turn scenarios |
|
- used the 4th ranking response as the "rejected" instead of the 3rd. When I inspected the dataset, I frequently could not find any meaningful difference in quality between the 1st and 3rd ranked responses, so to make the accepted/rejected signal extra clear, I replaced 3rd ranking with 4th ranking. |
|
- I filtered out any examples with "good_natured == False". Why? When I inspected examples with "good_natured == False" in the Nectar dataset, I noticed they frequently include refusals from even the top ranking model. So, counter-intuitively, including "bad natured" entries might actually censor the model *more*, since the top responses (as ranked by GPT-4) to these queries tend to be refusals. Not to mention, the quality of the conversations that are "bad natured" tends to be worse in general, in my own opinion. |
|
|
|
Differences from 0.4: |
|
- Trained on 5000 steps instead of 500, with a lower learning rate and slower warmup period. |
|
|
|
Summary of versions: |
|
|
|
**[openchat-nectar-0.1](https://huggingface.co/andysalerno/openchat-nectar-0.1)** |
|
- 200 steps, no filtering on Nectar dataset, 5e-5 learning rate |
|
|
|
**[openchat-nectar-0.2](https://huggingface.co/andysalerno/openchat-nectar-0.2)** |
|
- empty repo, failed training. ignore it |
|
|
|
**[openchat-nectar-0.3](https://huggingface.co/andysalerno/openchat-nectar-0.3)** |
|
- 500 steps, no filtering on Nectar dataset, 5e-5 learning rate (same as 1 but with more steps) |
|
|
|
**[openchat-nectar-0.4](https://huggingface.co/andysalerno/openchat-nectar-0.4)** |
|
- 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 |
|
|
|
**[openchat-nectar-0.5](https://huggingface.co/andysalerno/openchat-nectar-0.5)** |
|
- 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 |
|
|
|
**[openchat-nectar-0.6](https://huggingface.co/andysalerno/openchat-nectar-0.6)** |
|
- 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 |
