Loss #8
Merged
Loss #8
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
The class checks the inputs. There's a trivial MLP implementation.
| """ | ||
| match hyper_params.name: | ||
| case ValidOptimizerNames.adam: | ||
| optimizer = optim.Adam(model.parameters(), lr=hyper_params.learning_rate) |
There was a problem hiding this comment.
depending on the regime, we might have to change the eps variable in adam. It might be premature to add it at this stage, it is easy enough to do later. Just something to keep in mind.
sblackburn86
approved these changes
Mar 20, 2024
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Outdated suggestions cannot be applied.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.
In this PR:
I also fixed a bug where I was sometimes computing$\sigma^2 S$ , and sometimes computing $\sigma S$ , but calling it the same thing.
Finally, I implement a "sanity check" experiment where I try to overfit a small dataset of random positions with a MLP score network. Despite fiddling around with parameters, you can see below that this model doesn't learn anything.
This is suspicious and will require further exploration. I don't know why this is happening, but my best guesses are
1- the data in fact keeps changing because we are sampling noise randomly: the model doesn't see the same batch over and over
2- an MLP is really crappy.