Instructions to use Commandante/german-party-sentiment-bert-241-synonyms-5e-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Commandante/german-party-sentiment-bert-241-synonyms-5e-5 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Commandante/german-party-sentiment-bert-241-synonyms-5e-5")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Commandante/german-party-sentiment-bert-241-synonyms-5e-5") model = AutoModelForSequenceClassification.from_pretrained("Commandante/german-party-sentiment-bert-241-synonyms-5e-5", device_map="auto") - Notebooks
- Google Colab
- Kaggle
german-party-sentiment-bert-241-synonyms-5e-5
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: 0.9680
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 |
|---|---|---|---|
| 1.3705 | 1.0 | 28 | 0.9724 |
| 0.9826 | 2.0 | 56 | 0.9680 |
| 0.9826 | 3.0 | 84 | 0.9769 |
| 0.8121 | 4.0 | 112 | 1.0368 |
| 0.8121 | 5.0 | 140 | 1.1361 |
| 0.5266 | 6.0 | 168 | 1.4722 |
| 0.2635 | 7.0 | 196 | 1.3610 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Tokenizers 0.15.1
- Downloads last month
- 2
Model tree for Commandante/german-party-sentiment-bert-241-synonyms-5e-5
Base model
mdraw/german-news-sentiment-bert