DanishMahdi/Sindhi_News_cat

results

This model is a fine-tuned version of xlm-roberta-base on Sindhi news category dataset. It achieves the following results on the evaluation set:

• Loss: 0.0612
• Accuracy: 0.9911
• F1: 0.9911

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use 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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.0829	1.0	337	0.1015	0.9822	0.9822
0.1932	2.0	674	0.0777	0.9852	0.9852
0.0645	3.0	1011	0.0612	0.9911	0.9911
0.0004	4.0	1348	0.0625	0.9911	0.9911

Framework versions

• Transformers 4.53.0
• Pytorch 2.7.1+cu126
• Datasets 3.6.0
• Tokenizers 0.21.1