bert-base-german-cased-finetuned-squad
This model is a fine-tuned version of bert-base-german-cased on the germanquad dataset. It achieves the following results on the evaluation set:
- Loss: 2.6468
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|
| No log | 1.0 | 180 | 1.9940 |
| No log | 2.0 | 360 | 1.7339 |
| 2.5168 | 3.0 | 540 | 1.8300 |
| 2.5168 | 4.0 | 720 | 1.9861 |
| 2.5168 | 5.0 | 900 | 2.1922 |
| 0.6891 | 6.0 | 1080 | 2.3542 |
| 0.6891 | 7.0 | 1260 | 2.4410 |
| 0.6891 | 8.0 | 1440 | 2.5836 |
| 0.2347 | 9.0 | 1620 | 2.6020 |
| 0.2347 | 10.0 | 1800 | 2.6468 |
Framework versions
- Transformers 4.27.2
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2