Training fixes #53
Merged
Training fixes #53
Conversation
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
added 9 commits
October 31, 2025 13:06
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
benjamin-elder
force-pushed
the
training_fixes
branch
from
76a923a to
2046bad
Compare
added 4 commits
October 31, 2025 13:29
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
benjamin-elder
force-pushed
the
training_fixes
branch
from
33e0ffd to
5b87887
Compare
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
Co-authored-by: siyuhuo <[email protected]>
Signed-off-by: Benjamin Elder [email protected] <[email protected]>
AnkitaNaik
approved these changes
Nov 13, 2025
| print(f"Datasets Loaded for {format} turn data.") | ||
| print("------------------------------------------------------------------------------------------------------------------------------------------------------------------------------") | ||
| assert set(data_no_scenarios_dict.keys()) == set(data_with_scenario_dict.keys()) | ||
| # assert set(data_no_scenarios_dict.keys()) == set(data_with_scenario_dict.keys()) |
Collaborator
There was a problem hiding this comment.
Is this assertion not valid in exploratory trajectories? @benjamin-elder
Collaborator
Author
There was a problem hiding this comment.
@AnkitaNaik yeah that seems to be the case. The alternate traces are sort of randomly dispersed I guess, so there's no guarantee that you won't have a case where the non-scenario doesn't have one and the scenario does, or vice-versa.
| from transformers import AutoModelForCausalLM, AutoTokenizer | ||
| device = "auto" | ||
| model_path = "ibm-granite/granite-3.0-8b-base" | ||
| model_path = "ibm-granite/granite-4.0-micro" |
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.
Changes to the training loader to use context response pairs.
Changes to tool call env and evaluation.py to enable parallel/multiprocess inference.