metadata
base_model: smanjil/German-MedBERT
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: German-MedBERT
results: []
German-MedBERT
This model is a fine-tuned version of smanjil/German-MedBERT on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6756
- F1: 0.5231
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 |
|---|---|---|---|---|
| 0.6685 | 1.0 | 189 | 0.6026 | 0.0 |
| 0.6161 | 2.0 | 378 | 0.5464 | 0.2326 |
| 0.569 | 3.0 | 567 | 0.5510 | 0.2273 |
| 0.5636 | 4.0 | 756 | 0.5546 | 0.3704 |
| 0.5668 | 5.0 | 945 | 0.5323 | 0.4571 |
| 0.4882 | 6.0 | 1134 | 0.7460 | 0.3265 |
| 0.5819 | 7.0 | 1323 | 0.6150 | 0.4776 |
| 0.4747 | 8.0 | 1512 | 0.6596 | 0.4923 |
| 0.5035 | 9.0 | 1701 | 0.6764 | 0.5 |
| 0.463 | 10.0 | 1890 | 0.6756 | 0.5231 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.2
- Datasets 2.12.0
- Tokenizers 0.13.3