examples(eval-callback): Eval callback verbosity#17028
Open
gabe-l-hart wants to merge 3 commits intoggml-org:masterfrom
Open
examples(eval-callback): Eval callback verbosity#17028gabe-l-hart wants to merge 3 commits intoggml-org:masterfrom
gabe-l-hart wants to merge 3 commits intoggml-org:masterfrom
Conversation
…elements Branch: Mamba2SSD Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Branch: Mamba2SSD Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Collaborator
Author
|
As I was making the PR, I think the |
…idth Branch: EvalCallbackVerbosity Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
Closed
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
This PR is extracted from #16982 since it's an isolated change that's not strictly related to implementing the SSD algorithm.
The changes in this PR add the ability to print more verbose tensors with
llama-eval-callback. There are two higher-verbosity states available:-lv 1: Print all tensors with 8 digits of presion instead of 5-lv >1: Print all tensors with 8 digits of presion instead of 5 AND print all tensor values rather than the slimmed begin/end view (this is VERY verbose!)Sample Output
Current (no
-lv)-lv 1/--verbose-lv 2WARNING: It's best to redirect this to a file!
output