distilbert-ag-news-classifier

This model is a fine-tuned version of distilbert/distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1841
• Accuracy: 0.947
• F1: 0.9467

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: 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	Accuracy	F1
0.1879	1.0	3750	0.1721	0.941	0.9407
0.1351	2.0	7500	0.1701	0.946	0.9461
0.0878	3.0	11250	0.1841	0.947	0.9467

Framework versions

• Transformers 4.53.3
• Pytorch 2.6.0+cu124
• Datasets 4.4.1
• Tokenizers 0.21.2