metadata
license: mit
base_model: bert-base-german-cased
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: Germeval24StageTask2
results: []
Germeval24StageTask2
This model is a fine-tuned version of bert-base-german-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5740
- Precision: 1.0
- Recall: 1.0
- F1: 1.0
- Accuracy: 0.7979
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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 175 | 0.6167 | 1.0 | 1.0 | 1.0 | 0.7589 |
| No log | 2.0 | 350 | 0.5740 | 1.0 | 1.0 | 1.0 | 0.7979 |
| 0.5186 | 3.0 | 525 | 0.8370 | 1.0 | 1.0 | 1.0 | 0.7719 |
| 0.5186 | 4.0 | 700 | 0.7648 | 1.0 | 1.0 | 1.0 | 0.8153 |
| 0.5186 | 5.0 | 875 | 0.7703 | 1.0 | 1.0 | 1.0 | 0.7988 |
| 0.1581 | 6.0 | 1050 | 0.8545 | 1.0 | 1.0 | 1.0 | 0.8092 |
| 0.1581 | 7.0 | 1225 | 0.9456 | 1.0 | 1.0 | 1.0 | 0.8057 |
| 0.1581 | 8.0 | 1400 | 1.0018 | 1.0 | 1.0 | 1.0 | 0.8031 |
| 0.0573 | 9.0 | 1575 | 1.0635 | 1.0 | 1.0 | 1.0 | 0.8066 |
| 0.0573 | 10.0 | 1750 | 1.0481 | 1.0 | 1.0 | 1.0 | 0.8066 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1