You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
RESPONSE consumed by ROUGEScoreMetric function, gets a lot longer text than is expected based on the output_features and max_sequence_length. Even when the max_sequence_length is 8 or 16 tokens, it RESPONSE contains the text which is as long as the text in prompt_template.
Based on my investigation, it is happening because in get_decoded_targets_and_predictions condition is wrong, instead of targets != IGNORE_INDEX_TOKEN_ID, it is set to predictions[PREDICTIONS] != IGNORE_INDEX_TOKEN_ID. From what I understand we should be using the targets index to truncate the predictions correctly.
When I apply this change I get the correct metric value, matching up with the expectations given the results seen during finetuning
Python version: 3.11
Ludwig version: 0.10.1
The text was updated successfully, but these errors were encountered:
RESPONSE
consumed byROUGEScoreMetric
function, gets a lot longer text than is expected based on theoutput_features
andmax_sequence_length
. Even when themax_sequence_length
is 8 or 16 tokens, itRESPONSE
contains the text which is as long as the text inprompt_template
.Based on my investigation, it is happening because in
get_decoded_targets_and_predictions
condition is wrong, instead oftargets != IGNORE_INDEX_TOKEN_ID
, it is set topredictions[PREDICTIONS] != IGNORE_INDEX_TOKEN_ID
. From what I understand we should be using the targets index to truncate the predictions correctly.When I apply this change I get the correct metric value, matching up with the expectations given the results seen during finetuning
The text was updated successfully, but these errors were encountered: