metadata
license: mit
tags:
- generated_from_trainer
datasets:
- germanquad
model-index:
- name: bert-base-german-cased-finetuned-squad
results: []
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: 2.5718
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 |
|---|---|---|---|
| 2.959 | 1.0 | 930 | 1.3259 |
| 1.4632 | 2.0 | 1860 | 1.2816 |
| 0.954 | 3.0 | 2790 | 1.4692 |
| 0.6371 | 4.0 | 3720 | 1.6610 |
| 0.4482 | 5.0 | 4650 | 1.8121 |
| 0.3169 | 6.0 | 5580 | 1.9942 |
| 0.2021 | 7.0 | 6510 | 2.2969 |
| 0.147 | 8.0 | 7440 | 2.4245 |
| 0.1132 | 9.0 | 8370 | 2.5011 |
| 0.0858 | 10.0 | 9300 | 2.5718 |
Framework versions
- Transformers 4.27.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2