Automatically calculate perplexity metrics for model supportability #1008
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
fajin-corp
reviewed
Oct 24, 2024
| targets = np.roll(input_ids, -1, axis=1) | ||
|
|
||
| # Use LogSoftMax here | ||
| log_probs = torch.nn.functional.log_softmax(torch.tensor(logits), dim=1).numpy() |
fajin-corp
reviewed
Oct 24, 2024
| log_probs = torch.nn.functional.log_softmax(torch.tensor(logits), dim=1).numpy() | ||
|
|
||
| batch_size, seq_length = targets.shape | ||
| target_log_probs = log_probs[np.arange(batch_size)[:, None], np.arange(seq_length), targets] |
fajin-corp
reviewed
Oct 25, 2024
| total_log_probs = 0 | ||
| total_token_count = 0 | ||
|
|
||
| for batch in dataset: |
fajin-corp
reviewed
Oct 25, 2024
|
|
||
| logits = generator.compute_logits("logits") | ||
|
|
||
| targets = np.roll(input_ids, -1, axis=1) |
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Outdated suggestions cannot be applied.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.
This PR aims to enhance our model validation process by automatically calculating the perplexity metrics if the model has the corresponding dataset. This will allow us to generate a strong report on the model's supportability, providing valuable insights into its performance and reliability.