metadata
license: mit
base_model: bert-base-german-cased
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: Misinformation-Covid-bert-base-german-cased
results: []
Misinformation-Covid-bert-base-german-cased
This model is a fine-tuned version of bert-base-german-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8485
- F1: 0.5366
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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.6693 | 1.0 | 201 | 0.6232 | 0.4 |
| 0.5901 | 2.0 | 402 | 0.5644 | 0.4321 |
| 0.5235 | 3.0 | 603 | 0.5257 | 0.5192 |
| 0.4525 | 4.0 | 804 | 0.5301 | 0.5149 |
| 0.4244 | 5.0 | 1005 | 0.6341 | 0.5349 |
| 0.4167 | 6.0 | 1206 | 0.6546 | 0.5169 |
| 0.3718 | 7.0 | 1407 | 0.7417 | 0.5366 |
| 0.3626 | 8.0 | 1608 | 0.8642 | 0.5455 |
| 0.3884 | 9.0 | 1809 | 0.8662 | 0.5385 |
| 0.3962 | 10.0 | 2010 | 0.8485 | 0.5366 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.2
- Datasets 2.12.0
- Tokenizers 0.13.3