From a099634802195e4a13c050d3ac62c8fec842a7a7 Mon Sep 17 00:00:00 2001 From: Daniel Hladek Date: Mon, 4 Aug 2025 14:13:40 +0200 Subject: [PATCH] zz --- pages/interns/yussef_ressaissi/README.md | 25 ++++++++++++++++++++++-- 1 file changed, 23 insertions(+), 2 deletions(-) diff --git a/pages/interns/yussef_ressaissi/README.md b/pages/interns/yussef_ressaissi/README.md index 1ac6eb13..8fd60ccd 100644 --- a/pages/interns/yussef_ressaissi/README.md +++ b/pages/interns/yussef_ressaissi/README.md @@ -30,6 +30,27 @@ Tasks: - Prepare a final report with analysis, experiments and conclusions. - Publish the fine-tuned models in HF HUB. Publish the paper from the project. +Meeting 4.8. + +State: + +- Tested LMs with ROUGE metrics, most models got 4-5 ROGUE, facebook/mbart-large-50 got 17 (trained for translation). +- In my opinion, large-50 is not good for finetuning, because it is already fine tuned for translation. +- no finetuning done yet. + +Tasks: + +- Try evaluate google/flan-t5-large, kiviki/mbart-slovaksum-large-sum and similar models. These should be already working. +- continue working on finetuning t5 or Mbart models, but ask when you are stuck. Use hf examples script on summarization + +Future tasks: + +- use LLMS (open or closed) and evaluate (ROUGE) summarization without fine-tuning on slovak legal data set +- install lm-eval-harness, learn it, prepare and run task for slovak summarization + + + + Meeting 24.7. State: @@ -50,8 +71,8 @@ State: - Studying of the task, metrics (ROUGE,BLEU) - Loaded a model. preprocessed a dataset, evaluated a model -- loaded more models, used SlovakSum, generated summarization with four model and comapre them with ROUGE and BLEU (TUKE-KEMT/slovak-t5-base, google/mt5-small, google/mt5-base, facebook/mbart-large-50) -- the comparisin is without fine tuning (zero shot), for far, the best is MBART-large +- loaded more models, used SlovakSum, generated summarization with four model and compare them with ROUGE and BLEU (TUKE-KEMT/slovak-t5-base, google/mt5-small, google/mt5-base, facebook/mbart-large-50) +- the comparison is without fine tuning (zero shot), for far, the best is MBART-large - working on legal dataset "dennlinger/eur-lex-sum", - notebooks are on the kemt git