metadata
license: mit
base_model: oliverguhr/german-sentiment-bert
tags:
- generated_from_trainer
model-index:
- name: german-sentiment-bert-retrained-20240110
results: []
german-sentiment-bert-retrained-20240110
This model is a fine-tuned version of oliverguhr/german-sentiment-bert on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6099
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 |
|---|---|---|---|
| 2.5995 | 1.0 | 3 | 1.8235 |
| 2.5995 | 2.0 | 6 | 1.8114 |
| 2.5995 | 3.0 | 9 | 1.7902 |
| 2.5995 | 4.0 | 12 | 1.7628 |
| 2.5995 | 5.0 | 15 | 1.7234 |
| 2.5995 | 6.0 | 18 | 1.6716 |
| 2.5995 | 7.0 | 21 | 1.6099 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Tokenizers 0.15.0