for ex: I have four classes class 1: 200 samples class 2: 100 samples class 3: 20 samples class 4: 10 samples so during predictions, most of my samples are predicting class 1 or 2 because samples are high even I have unlabeled samples of class3 and class4. How can I overcome this in HF? is it…

How to give equal importance of all labels while dealing with unbalanced samples

marshmellow77 January 28, 2022, 6:37am 5

Topic		Replies	Views
How can I use class_weights when training? 🤗Transformers	19	31384	December 29, 2022
How to dealing with Data Imbalance 🤗Datasets	2	6436	July 28, 2020
Handling Extreme Class Imbalance for Multi-Class Classification Intermediate	1	176	May 14, 2025
Unbalanced dataset for text classification - best practice Beginners	0	306	March 21, 2024
Imbalanced data in ner task 🤗Transformers	0	637	February 3, 2023