TURNA based Finetuned Dictionary
This model is a finetuned model. The aim is make TURNA specialized for dictionary task.
DATASET
This model is finetuned with https://www.kaggle.com/datasets/erogluegemen/tdk-turkish-words dataset.
TRAINING DETAILS
We have randomly take 10000 samples from the above dataset. And used them for fine tuning of Turna
Results Epoch (Training Loss) (Validation Loss) (Rouge1) (Rouge2) (Rougel) (Rougelsum) (Gen Len) 1 2.804800 2.400238 18.491200 11.147300 18.124600 18.134400 19.000000