metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- f1
base_model: distilbert-base-uncased
model-index:
- name: media-bias-ukraine-dataset-all-minus-ukraine
results: []
media-bias-ukraine-dataset-all-minus-ukraine
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: 2.4742
- F1: 0.2408
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 |
|---|---|---|---|---|
| 0.0979 | 1.0 | 138 | 2.1940 | 0.1065 |
| 0.1215 | 2.0 | 276 | 2.3970 | 0.2096 |
| 1.1233 | 3.0 | 414 | 2.0863 | 0.1919 |
| 0.0041 | 4.0 | 552 | 2.6282 | 0.1823 |
| 0.0141 | 5.0 | 690 | 2.9322 | 0.1994 |
| 0.0348 | 6.0 | 828 | 2.4742 | 0.2408 |
| 0.0018 | 7.0 | 966 | 2.8876 | 0.1986 |
| 0.0014 | 8.0 | 1104 | 3.1422 | 0.1878 |
| 0.0044 | 9.0 | 1242 | 3.0119 | 0.2142 |
| 0.5136 | 10.0 | 1380 | 2.9972 | 0.2082 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.10.1
- Tokenizers 0.13.2