<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
roberta-base-wechsel-german-finetuned-germanquad
This model is a fine-tuned version of benjamin/roberta-base-wechsel-german on the germanquad dataset. It achieves the following results on the evaluation set:
- Loss: 2.0401
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 | 2.7806 |
No log | 2.0 | 360 | 2.5746 |
2.7322 | 3.0 | 540 | 2.4898 |
2.7322 | 4.0 | 720 | 1.6754 |
2.7322 | 5.0 | 900 | 1.6187 |
1.0385 | 6.0 | 1080 | 1.7933 |
1.0385 | 7.0 | 1260 | 1.8615 |
1.0385 | 8.0 | 1440 | 1.9606 |
0.4498 | 9.0 | 1620 | 1.9858 |
0.4498 | 10.0 | 1800 | 2.0401 |
Framework versions
- Transformers 4.27.2
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2