ContinualAI/avalanche

Using validation set for early stopping

Open

#904 opened on Feb 4, 2022

View on GitHub
 (0 comments) (0 reactions) (0 assignees)Python (258 forks)batch import
Evaluationbuggood first issue

Repository metrics

Stars
 (1,516 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

Discussed in https://github.com/ContinualAI/avalanche/discussions/900

Originally posted by sivomke January 30, 2022 Hi, everyone!

I have created a benchmark with dataset_benchmark that contains 3 experiences, and then have added a validation set to this benchmark with benchmark_with_validation_stream. I am trying to use Early Stopping with validation set: for each experience, I would like to use loss on the validation set of the corresponding experience. I have indicated metric_name = 'Loss_Exp' and val_stream_name='valid' , however, it still uses Loss_Exp/eval_phase/train_stream of the corresponding experience instead. Could you please tell me what would be the correct way to use validation set for early stopping?

Here is the script

Thank you!

Contributor guide

Research direction
Investigate the EarlyStop callback implementation in Avalanche to understand how it selects the stream for validation metrics. Focus on the `metric name` and `val stream name` parameters. Determine why specifying `val stream name='valid'` does not override the default behavior of using the training stream. Check the benchmark creation and validation stream assignment.
Tech stack
pythonpytorch
Domain
machine learning
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Needs maintainer response
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
65