german-party-sentiment-bert-111-synonyms
This model is a fine-tuned version of mdraw/german-news-sentiment-bert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0635
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: 8e-06
- train_batch_size: 20
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 120
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2178 | 1.0 | 25 | 1.1090 |
| 1.1258 | 2.0 | 50 | 1.0695 |
| 1.1258 | 3.0 | 75 | 1.0635 |
| 1.0362 | 4.0 | 100 | 1.0968 |
| 1.0362 | 5.0 | 125 | 1.1286 |
| 0.9433 | 6.0 | 150 | 1.1412 |
| 0.9433 | 7.0 | 175 | 1.1431 |
Framework versions
- Transformers 4.37.1
- Pytorch 2.1.2+cu118
- Tokenizers 0.15.1
- Downloads last month
- 3
Model tree for Commandante/german-party-sentiment-bert-111-synonyms
Base model
mdraw/german-news-sentiment-bert