Modality change, fixed 250 epochs, and seeded splits logic #10
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
to 50 and 250 respectively. Timeouts will still apply to stop early if it is taking too long. Amount of training completed will be computed off of these new maxes, i.e. training_completed of 1.0 will mean all of the 250 batches were trained. With this change we will want model updates to be counted according to local data size, therefore it is important that the training config set the train_completion_dampener at the value: 0.0.
…s related to his new initial model: order = t1 t2 flair t1c
brandon-edwards
temporarily deployed
to
testing-external-code
GitHub Actions
Inactive
brandon-edwards
temporarily deployed
to
testing-external-code
GitHub Actions
Inactive
brandon-edwards
temporarily deployed
to
testing-external-code
GitHub Actions
Inactive
hasan7n
temporarily deployed
to
testing-external-code
GitHub Actions
Inactive
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Outdated suggestions cannot be applied.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.
Modality is now fixed for the new initial model
Val and training batch counts are set at 50 and 250 as is done in NNUnet (with timouts still in place)
Train_completion dampener is set to 0.0 in the trianing_config I provide here (can bring over other plan of course but set this the same if so).
Splits logic is seeded to be reproducible
Splits logic tested independently with different seeds to see difference and reproducibility