media-bias-ukraine-dataset-all-minus-ukraine-masked
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.1320
- F1: 0.1873
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.4073 | 1.0 | 138 | 2.2614 | 0.1325 |
| 0.0399 | 2.0 | 276 | 2.0816 | 0.1332 |
| 0.2509 | 3.0 | 414 | 2.8722 | 0.1637 |
| 0.0338 | 4.0 | 552 | 3.1320 | 0.1873 |
| 0.0056 | 5.0 | 690 | 3.5202 | 0.1682 |
| 0.0064 | 6.0 | 828 | 3.4360 | 0.1696 |
| 0.0011 | 7.0 | 966 | 3.4185 | 0.1714 |
| 0.0023 | 8.0 | 1104 | 3.4920 | 0.1694 |
| 0.0011 | 9.0 | 1242 | 3.6794 | 0.1722 |
| 0.0018 | 10.0 | 1380 | 3.6641 | 0.1702 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.10.1
- Tokenizers 0.13.2