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: 0.7182
- F1: 0.3333
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 |
|---|---|---|---|---|
| 0.6609 | 1.0 | 189 | 0.6062 | 0.0 |
| 0.6168 | 2.0 | 378 | 0.5649 | 0.1818 |
| 0.5638 | 3.0 | 567 | 0.5665 | 0.1818 |
| 0.5382 | 4.0 | 756 | 0.5790 | 0.2128 |
| 0.5399 | 5.0 | 945 | 0.5459 | 0.3284 |
| 0.4745 | 6.0 | 1134 | 0.7525 | 0.3265 |
| 0.5061 | 7.0 | 1323 | 0.6379 | 0.3529 |
| 0.377 | 8.0 | 1512 | 0.6965 | 0.3692 |
| 0.4159 | 9.0 | 1701 | 0.7172 | 0.3478 |
| 0.3924 | 10.0 | 1890 | 0.7182 | 0.3333 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.2
- Datasets 2.12.0
- Tokenizers 0.13.3