This model is a fine-tuned version of bert-base-uncased optimized to classify articles into 5 categories (Business, Tech, Politics, Sports, Entertainment).

Model Description

Architecture: BERT-base-uncased with frozen base layers for training efficiency.
Task: Multi-class Text Classification (NLP Pipeline).
Performance: Achieved a 0.96 Macro-F1 score on evaluation.

Training and Evaluation Data

Dataset: BBC News Dataset.
Preprocessing: Cleaned text fields tokenized using the standard BERT WordPiece tokenizer.

Intended Uses & Limitations

This model is intended for production-ready news classification pipelines. It is lightweight due to layer-freezing optimization during training.

bert-BBc-classifier

This model is a fine-tuned version of google-bert/bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0873

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: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss
0.0635	1.0	213	0.1708
0.0695	2.0	426	0.1116
0.0677	3.0	639	0.0842
0.0525	4.0	852	0.0882
0.0511	5.0	1065	0.0873

Framework versions

Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1

BluSerK/bert-BBc-classifier

BERT News Category Classifier

Model Description

Training and Evaluation Data

Intended Uses & Limitations

bert-BBc-classifier

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

BluSerK/
bert-BBc-classifier