Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add fine tuning experiment #88

Merged
merged 3 commits into from
Sep 12, 2023
Merged

Add fine tuning experiment #88

merged 3 commits into from
Sep 12, 2023

Conversation

steventkrawczyk
Copy link
Contributor

No description provided.

Copy link
Collaborator

@NivekT NivekT left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks good to me! Thank you for adding this. Just small comments:

  1. Might need to ask users to install datasets from HuggingFace up top
  2. Is file-name on this line openai.FineTuningJob.create(training_file="file-name", model="gpt-3.5-turbo") correct? I guess that may be the default name?
  3. How long does the fine-tuning job take? We can mention that as well so they know what to expect.

I think adding a SQL syntax validator (as an eval function) in the future can be cool.

Comment on lines 44 to 48
dfs_to_concat = [df[columns_with_multiple_unique_values], df[unhashable_columns]]
if 'prompt' in df:
dfs_to_concat.append(df['prompt'])
if 'messages' in df:
dfs_to_concat.append(df['messages'])
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Might need to check if it already exists in dfs_to_concat . Otherwise, you might get duplicate? Unless pd.concat handles duplication

Copy link
Contributor Author

@steventkrawczyk steventkrawczyk Sep 12, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Good catch! I updated the logic to avoid duplicates

@steventkrawczyk
Copy link
Contributor Author

Looks good to me! Thank you for adding this. Just small comments:

  1. Might need to ask users to install datasets from HuggingFace up top
  2. Is file-name on this line openai.FineTuningJob.create(training_file="file-name", model="gpt-3.5-turbo") correct? I guess that may be the default name?
  3. How long does the fine-tuning job take? We can mention that as well so they know what to expect.

I think adding a SQL syntax validator (as an eval function) in the future can be cool.

  1. Added relevant installations to the top section
  2. Updated the name to make it more clear it's a placeholder.
  3. Added some notes, it could be a few hours for tuning.

Totally agree that validating SQL is a good one, added an issue here: #89

@steventkrawczyk steventkrawczyk merged commit 44d997c into main Sep 12, 2023
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants