Implement a finetuning feature #73
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ndant classes; use same MLPs as encoders
- Use cross-validation to pick best learning rate; reset model at every fold - Use early stopping - Move the tuning experiments into the class - Temporarily removed the freeze operations
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The user can decide to use a portion of the test dataset to fine-tune a model trained on the train dataset.
The user can set "--finetuning_samples" to a number of samples to be used for finetuning.
A 5-fold cross-validation scheme is used to test different learning rates and model parameter freezing strategies (freezing the encoders or supervisors or neither) to find the best setup. A final model is built on the finetuning samples. The fine-tuned model is evaluated on the remaining test samples.