distilbert-ag-news-finetuned
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6827
- Accuracy: 0.908
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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: cosine
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7787 | 1.0 | 313 | 0.7052 | 0.8935 |
| 0.5994 | 2.0 | 626 | 0.5796 | 0.908 |
| 0.4470 | 3.0 | 939 | 0.5805 | 0.906 |
| 0.3272 | 4.0 | 1252 | 0.5873 | 0.911 |
| 0.2496 | 5.0 | 1565 | 0.6183 | 0.909 |
| 0.1958 | 6.0 | 1878 | 0.6827 | 0.908 |
Framework versions
- Transformers 5.8.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2