mehtayash12345678/mlops-ag_news_classification-distilbert
028
DistilBERT fine-tuned on AG News
This model is a fine-tuned version of distilbert-base-uncased on the AG News 4-class news topic classification dataset.
Performance (V3)
Hyperparameters
- Learning rate: 3e-05
- Batch size: 32
- Epochs: 3
- Weight decay: 0.01
- Warmup ratio: 0.1
- Max length: 128
- Mixed precision: FP16
- Seed: 42
