added datasets and models for text generation evaluation #291
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
|
Thanks, this is great! Can you also run these evals and add the numbers to the leaderboard readme? |
kaustubhdhole
requested review from
mille-s,
Saad-Mahamood and
sebastianGehrmann
|
@ashish3586 can you please provide a short description of your transformation? |
Saad-Mahamood
requested changes
Sep 30, 2021
aadesh11
reviewed
Oct 29, 2021
| dataset = KeyValueDataset.from_huggingface( | ||
| hf_dataset, TaskType.TEXT_TO_TEXT_GENERATION, ["text", "summary"] | ||
| ) | ||
|
|
There was a problem hiding this comment.
Missing return statement for "billsum".
aadesh11
reviewed
Oct 29, 2021
| dataset = KeyValueDataset.from_huggingface( | ||
| hf_dataset, TaskType.TEXT_TO_TEXT_GENERATION, ["text", "summary"] | ||
| ) | ||
|
|
There was a problem hiding this comment.
Also, I would suggest adding the 'else' block and raising exceptions with the proper message.
aadesh11
reviewed
Oct 29, 2021
| "summarization", model=model_name, tokenizer=model_name | ||
| "summarization", model=model_name, tokenizer=model_name, device=0 if is_cuda else -1) | ||
| #percent = f"[{split.split('[')[-1]}" if "[" in split else "" | ||
| #if dataset_name == "wikihow": split = "all[:1%]" # f"all{percent}" |
There was a problem hiding this comment.
I think we can remove this commented code.
aadesh11
reviewed
Oct 29, 2021
| #if dataset_name == "wikihow": split = "all[:1%]" # f"all{percent}" | ||
|
|
||
| dataset = _process_data(dataset_name, split) | ||
| print( |
There was a problem hiding this comment.
Duplicate print statement.
aadesh11
reviewed
Oct 29, 2021
| references = [] | ||
| raw_hypotheses = [] | ||
| print(f"Length of Evaluation dataset is {len(dataset)}") | ||
|
|
||
| for example in dataset: | ||
| for i,example in enumerate(dataset): | ||
| print(i) |
There was a problem hiding this comment.
Do we need this print statement?
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.
No description provided.