metadata
license: mit
base_model: oliverguhr/german-sentiment-bert
tags:
- generated_from_trainer
model-index:
- name: german-party-sentiment-bert-complete-gsbert
results: []
German-Party-Sentiment-Bert
This model is a fine-tuned version of oliverguhr/german-sentiment-bert on a dataset consisting of mentions of german political parties. It achieves the following results on the evaluation set:
- Loss: 0.8912
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: 5e-05
- 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 |
|---|---|---|---|
| 1.2844 | 1.0 | 65 | 0.9382 |
| 0.9704 | 2.0 | 130 | 0.8912 |
| 0.7394 | 3.0 | 195 | 1.0455 |
| 0.5401 | 4.0 | 260 | 1.2711 |
| 0.4274 | 5.0 | 325 | 1.3578 |
| 0.2289 | 6.0 | 390 | 1.6143 |
| 0.1949 | 7.0 | 455 | 1.8376 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Tokenizers 0.15.1