This is the seventh (Lucky!) in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. This model is fine-tuned on top of Qwen-2 72B Instruct.
Prompting
Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:
py
1"""<|im_start|>user
2Hi there!<|im_end|>
3<|im_start|>assistant
4Nice to meet you!<|im_end|>
5<|im_start|>user
6Can I ask a question?<|im_end|>
7<|im_start|>assistant
8"""
We also trained with a weight decay of 0.01 to help further stabilize the loss trajectory and mitigate catastrophic forgetting, and utilize a peak learning rate of 4e-6 to prevent the 2nd epoch loss from dropping too significantly (as it is a strong indicator of overfitting).
image/png
Sample Packing was done for 16k tokens rather than the 8k tokens used in our previous runs.
