If you have already fine-tuned a model for your task and now have additional training data that you would like to incorporate, you can continue fine-tuning from the model. This creates a model that has learned from all of the training data without having to re-train from scratch.
To do this, pass in the fine-tuned model name when creating a new fine-tuning job (e.g., -m curie:ft-<org>-<date>). Other training parameters do not have to be changed, however if your new training data is much smaller than your previous training data, you may find it useful to reduce learning_rate_multiplier by a factor of 2 to 4.
The documentation says nothing about which option is better in terms of which would yield better results.
However...
Choose Option 2
Why?
When training a fine-tuned model, the total tokens used will be billed according to our training rates.
If you choose Option 1, you'll pay for some tokens in your training dataset twice. First when doing fine-tuning with initial training dataset, second when doing fine-tuning with bigger training dataset (i.e., bigger-training-dataset.jsonl = initial-training-dataset.jsonl + additional-training-dataset.jsonl).
It's better to continue fine-tuning from a fine-tuned model because you'll pay only for tokens in your additional training dataset.
发布评论
评论（1）
更新
如官方 openai documentation ：
如官方 OpenAI文档：
选择哪个选项？
您正在询问两个选项：
ADA +大型训练dataset.jsonlada：ft-acme-inc-inc-2022-06-25 +附加培训-dataset.jsonl该文档没有说出哪个选项更好，哪种选项将产生更好的结果。
但是...
选择选项2
为什么？
如果您选择选项1，则两次在培训数据集中为某些令牌付费。首先，在使用初始培训数据集进行微调时，其次在使用更大的培训数据集进行微调时（IE，
较大训练dataset.jsonl=初始训练>初始训练dataset.jsonl < /code> + <代码>附加训练dataset.jsonl）。最好继续从微调模型中进行微调，因为您只需在其他培训数据集中为代币付费。
更多地了解微调定价计算。
UPDATE
It looks like fine-tuning a fine-tuned model is not supported anymore, as stated in the official OpenAI documentation:
As stated in the official OpenAI documentation:
Which option to choose?
You're asking about two options:
ada + bigger-training-dataset.jsonlada:ft-acme-inc-2022-06-25 + additional-training-dataset.jsonlThe documentation says nothing about which option is better in terms of which would yield better results.
However...
Choose Option 2
Why?
If you choose Option 1, you'll pay for some tokens in your training dataset twice. First when doing fine-tuning with initial training dataset, second when doing fine-tuning with bigger training dataset (i.e.,
bigger-training-dataset.jsonl=initial-training-dataset.jsonl+additional-training-dataset.jsonl).It's better to continue fine-tuning from a fine-tuned model because you'll pay only for tokens in your additional training dataset.
Read more about fine-tuning pricing calculation.