nyu-mll/glue
Viewer • Updated • 1.49M • 419k • 508
This model is a peft version of the roberta-large finetuned on the mrpc task of glue dataset
This model is finetuned on the mrpc task of Glue dataset which essentially compares two statements and decides and gets a label as to if they are equivalent or not. Dataset example is shown below
The model was tested on the testing set and gave an accuracy of 86.6% and F1 score of 90%
Similar fine tuning and evaluation can be done on the other tasks of the GLUE dataset by loading the correspodning config files or defining appropriate LORA config uing sample code :