metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: media-bias-ukraine-dataset-all-masked
results: []
media-bias-ukraine-dataset-all-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: 0.1585
- F1: 0.8205
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 |
|---|---|---|---|---|
| 0.321 | 1.0 | 114 | 0.2044 | 0.6280 |
| 0.3749 | 2.0 | 228 | 0.1678 | 0.8016 |
| 0.7008 | 3.0 | 342 | 0.1692 | 0.7832 |
| 0.0181 | 4.0 | 456 | 0.1585 | 0.8205 |
| 0.0513 | 5.0 | 570 | 0.1855 | 0.8022 |
| 0.0036 | 6.0 | 684 | 0.2107 | 0.7980 |
| 0.0396 | 7.0 | 798 | 0.2529 | 0.8017 |
| 0.0051 | 8.0 | 912 | 0.2397 | 0.7894 |
| 0.0062 | 9.0 | 1026 | 0.2698 | 0.7897 |
| 0.002 | 10.0 | 1140 | 0.2713 | 0.7878 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.10.1
- Tokenizers 0.13.2