bertbek-news-classifier

This model is a fine-tuned version of elmurod1202/bertbek-news-big-cased on the daryo news dataset elmurod1202/daryo_news_categorized. It achieves the following results on the evaluation set:

• Loss: 0.2955

Model description

BERTbek model fine-tuned for text classification

Intended uses & limitations

Text classification model for Uzbek texts

Training and evaluation data

Daryo news dataset: elmurod1202/daryo_news_categorized

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.22	1.0	3378	0.1993
0.1194	2.0	6756	0.2308
0.0633	3.0	10134	0.2955

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1