generated from alan-turing-institute/ARC-project-template
-
Notifications
You must be signed in to change notification settings - Fork 0
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
9 forgetting pipeline #18
Draft
jack89roberts
wants to merge
34
commits into
develop
Choose a base branch
from
9-forgetting-pipeline
base: develop
Could not load branches
Branch not found: {{ refName }}
Could not load tags
Nothing to show
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Draft
+3,150
−656
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
jack89roberts
added this to the Milestone 1: Working pipeline on small novel usecase milestone
Apr 25, 2024
jack89roberts
force-pushed
the
9-forgetting-pipeline
branch
2 times, most recently
from
May 3, 2024 17:13
7b122f7
to
2e186da
Compare
jack89roberts
force-pushed
the
9-forgetting-pipeline
branch
from
May 28, 2024 08:39
b8740ff
to
392151e
Compare
TOFU says it didn't work well
Steals a lot from fine-tuning branch - some placeholder forget configs and config classes - adds a data collator compatible with QAForgetDataset - adapts trainer loading etc. to have option of loading a forgetter instead BUG - Evaluation does not work, likely also needs adapting for expected data input format.
jack89roberts
force-pushed
the
9-forgetting-pipeline
branch
from
May 28, 2024 15:14
a877f2c
to
ad3522c
Compare
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.
Adds a
Forgetter
class for Gradient Ascent, Gradient Difference, KL, and "I don't know forgetters", which all inherit from the HuggingFaceTrainer
, only modifyingcompute_loss
.TODOs
Configs/Job Submission
All needs testing:
arcsf.config.experiment
has been adapted for the new config/job submission structure. It generates separate full, retain, and forget train scripts and configs.train.py
has been modified to accept the new config structure and to work for both training and forgetting jobs, but not checked/tested at all yet.Forgetting Evaluation
eval_dataset
/ any kind of evaluation during training as theevaluate
function in the trainer class doesn't know what to when given 2 data inputs (forget / retain). Theevaluate
function inarcsf.forget.base
need to be implemented to use Jack D's evaluation code (and the trainer should be initialised witheval_dataset
set to whatever our appropriate eval dataset instance is).