MSPoliBERT

This model is a fine-tuned version of bert-base-uncased on tnwei/ms-newspapers dataset. It achieves the following results on the evaluation set:

• Loss: 0.3062
• Accuracy: 0.9310

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8
• mixed_precision_training: Native AMP

Label Mappings

• 0: Economic Concerns
• 1: Racial discrimination or polarization
• 2: Leadership weaknesses
• 3: Development and infrastructure gaps
• 4: Corruption
• 5: Political instablility
• 6: Socials and Public safety
• 7: Administration
• 8: Education
• 9: Religion issues
• 10: Environmental
• 11: Others

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.3888	1.0	1138	0.3691	0.9178
0.2981	2.0	2276	0.3425	0.9240
0.2073	3.0	3414	0.3062	0.9310
0.1642	4.0	4552	0.3301	0.9336
0.1175	5.0	5690	0.3387	0.9345
0.1201	6.0	6828	0.3298	0.9358
0.1078	7.0	7966	0.3751	0.9327
0.0945	8.0	9104	0.3503	0.9349

Framework versions

• Transformers 4.18.0
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.12.1