Soyoung Yoon

icon indicating a website link soyoung97.github.io/profile icon indicating an email [email protected]

icon company https://ldilab-snu.notion.site/ldilab-snu/People-75efef1282f54ff1927a3f323d82c63d icon location Daejeon, South Korea icon location Graduate Student @ Seoul National University, Korea

Results 4 comments of Soyoung Yoon

Fine-tune broken for QRNNs?

Hi @daemon, I'm trying to work this finetune.py out. Can you tell me what you changed to make this work? I imported SplitCrossEntropyLoss and changed criterion on https://github.com/salesforce/awd-lstm-lm/blob/master/finetune.py#L115 and https://github.com/salesforce/awd-lstm-lm/blob/master/finetune.py#L146...

About m2 score evaluation

About the question - For evaluation of gleu, you can check out the README file at: https://github.com/soyoung97/Standard_Korean_GEC/tree/main/eval. About the m2 file evaluation - (I've written the code a long time...

MonoT5 .predict gives NaN

Hi, It's not exactly the same issue, but I've noticed similar issues on the _reranking_ task. For example, I'm using the following code. ``` def do_evaluation(queries, qrels, corpus, results=None): k_values...

[Bug?] uploaded monot5-large-msmarco-10k and monot5-large-msmarco model is exactly the same

Another example showing the weight of two models is exactly the same: (code from [here](https://discuss.pytorch.org/t/check-if-models-have-same-weights/4351/6))